SlideShare a Scribd company logo
Towards Billion Bit Optimization via Efficient
   Estimation of Distribution Algorithms

Kumara Sastry1,2 David E. Goldberg1, Xavier Llorà1,3
      1Illinois
             Genetic Algorithms Laboratory (IlliGAL)
          2Materials Computation Center (MCC)

3National Center for Super Computing Applications (NCSA)

University of Illinois at Urbana-Champaign, Urbana, IL 61801
        ksastry@uiuc.edu, deg@uiuc.edu, xllora@uiuc.edu
                      http://www.illigal.uiuc.edu


                  Supported by AFOSR FA9550-06-1-0096 and NSF DMR 03-25939.
                  Computational results were obtained using CSE’s Turing cluster.
Billion-Bit Optimization?
Strides w/ genetic algorithm (GA) theory/practice.
   Solving large, hard problems in principled way.
   Moving to practice in important problem domains.
Still GA boobirds claim:
(1) no theory, (2) too slow, and (3) just voodoo.
How demonstrate results achieved so far in dramatic way?
DEG lunch questions:
   A million? Sure.
   A billion? Maybe.
Naïve GA approach/implementation goes nowhere:
   ~100 terabytes memory for population storage.
   ~272 random number calls.
                                                           2
Roadmap
Motivation
Robust, scalable, and efficient GA designs
Toward billion-variable optimization
   Theory Keys
   Implementation Keys
   Efficiency Keys
   Results
Why this matters in practice?
Challenges to using this in real-world.
Summary and Conclusions


                                             3
Three Os and Million/Billion Decisions

The Os all have many decisions to
make:
   Nano, Bio, and Info
Modern systems increasingly complex:
   ~105 parts in a modern automobile
   ~107 parts in commercial jetliner.
Increased complexity increases appetite
for large optimization.
Will be driven toward routine
million/billion variable problems.
                                          “We get the warhead and
                                          then hold the world ransom
                                          for... 1 MILLION dollars!”


                                                                       4
Competent and Efficient GAs
Robust, scalable and efficient GA designs available.
Competence: Solve hard problems quickly, reliably, and
accurately (Intractable to tractable).
Efficiency: Develop speedup procedures (tractability to
practicality).
Principled design: [Goldberg, 2002]
   Relax rigor, emphasize scalability/quality.
   Use problem decomposition.
   Use facetwise models, and patchquilt integration using
   dimensional analysis.
   Test algorithms on adversarial problems


                                                            5
Aiming for a Billion
Theory & algorithms in place.
Focus on key theory, implementation, & efficiency
enhancements.
Theory keys:
   Problem difficulty.
   Parallelism.
Implementation key: compact GA.
Efficiency keys:
   Various speedup.
   Memory savings.
Results on a billion-variable noisy OneMax.


                                                    6
Theory Key 1: Master-Slave                     Linear Speedup

    Speed-up:


    Max speed-up at



    Near linear speed-up
    until




[Cantu-Paz & Goldberg, 1997; Cantú-Paz, 2000]
                                                                 7
Theory Key 2: Noise Covers Most Problems

 Adversarial problem design [Goldberg, 2002]


                       Fluctuating



                                      R
                   P                           Noise
     Deception            Scaling



 Blind noisy OneMax




                                                       8
Implementation Key: Compact GA
Simplest probabilistic model building GA [Harik, Lobo & Goldberg,
1997; Baluja, 1994; Mühlenbein & Paaß, 1996]

Represent population by probability vector
   Probability that ith bit is 1
Replace recombination with probabilistic sampling
Selectionist scheme
New population evolution through probability updates
Equivalent to GA with steady-state tournament selection
and uniform crossover




                                                                    9
Compact Genetic Algorithm (cGA)

Random initialization: Set probabilities to 0.5
Model Sampling: Generate two candidate solutions by
sampling the probability vector
Evaluation: Evaluate the fitness of two sampled solutions
Selection: Select the best among the sampled solutions
Probabilistic model update: Increase the proportion of
winning alleles by 1/n




                                                            10
Parallel cGA Architecture
  Processor #1                   Processor #2                          Processor #np



 Sample bits 1- l/np         Sample bits l/np+1- 2l/np         Sample bits (np-1)l/np+1- l


                       Collect partial sampled solutions and combine

                    Parallel fitness evaluation of sampled solutions

                       Broadcast fitness values of sampled solutions


Select best individual        Select best individual              Select best individual
Update probabilities           Update probabilities                Update probabilities



                                                                                           11
cGA is Memory Efficient: O(l) vs. O(l1.5)

                               Simple GA:


                               Compact GA:
                                  Frequencies instead of
                                  probabilities (4 bytes)
                                  Parallelization reduces
                                  memory per processor by
                                  factor of np

Orders of magnitude memory savings via efficient GA
Example: ~32 MB per processor on a modest 128
processors for billion-bit optimization
                                                            12
Vectorization Yields Speedup of 4

                                 Vectorize costly code
                                 segments with AltiVec/SSE2
                                    Generate 4 random numbers
                                    at a time
                                    Sample 4 bits at a time
                                    Update 4 probabilities at a
                                    time




SIMD instruction set allows vector operations on 128-bit
registers
Equivalent to 4 processors per processor
                                                              13
Other Efficiencies Yield Speedup of 15

Bitwise operations
Limited floating-point operations
Inline functions
Avoid using mod and division operations
Precomputing bit sums and indexing
Parallel, vectorized, and efficient GA:
   Memory scales as Θ(l/np); Speedup scales as 60np
   ~32 MB memory, and ~104 speedup with 128 processors
   Solves 65,536-bit noisy OneMax problem in ~45 minutes on
   a 3GHz PC.

                                                              14
Experimental Procedure
128 – 256 processor partition of 1280-processor Apple G5
Xserve
Population was doubled till cGA converged to at least l-1
out of l bits set to optimal values
For l > 223; Population size fixed according to theory.

Number of independent runs
   l ≤ 218 (262,144): 50
   l ≤ 225 (33, 554, 432): 10
   l > 225 (33, 554, 432): 1

Compare cGA performance with
   Sequential hillclimber (sHC)
   Random hillclimber (rHC)
                                                            15
Compact GA Population Sizing

                                              Noise-to-fitness
                                              variance ratio

Error tolerance                   # Components (# BBs)
   Signal-to-Noise ratio   # Competing sub-components


                                Additive Gaussian noise
                                with variance σ2N
                                Population sizing scales:
                                O(l0.5 log l)




                                          [Harik, et al, 1997]
                                                                 16
Compact GA Convergence Time

                                                                     Problem size (m·k )




                                                                 Selection Intensity

                                                  Convergence time
                                                  scales: O(m0.5)
                                                  GA scales as:
                                                  O(m log m)




[Miller & Goldberg, 1995; Goldberg, 2002; Sastry & Goldberg, 2002]                   17
Scalability on OneMax




                        18
EDA Solves Billion-Bit Noisy OneMax

               GA scales Θ(l·logl·(1+σ2N/σ2f))




Solved 33 million (225) bit problem to optimality.
Solved 1.1 billion (230) bit problem with relaxed, but
guaranteed convergence
                                                         19
Do Problems Like This Matter?
     Yes, for three reasons:
          Many GAs no more sophisticated than cGA.
          Inclusion of noise was important because it covers an
          important facet of difficulty.
          Know how to handle deception and other problems through
          EDAs like hBOA.
     Compact GA-like algorithms can solve tough problems:
          Material science [Sastry et al, 2004; Sastry et al, 2005]*
          Chemistry [Sastry et al, 2006]**.

     Complex versions of these kinds of problems need
     million/billion-bit optimization.


*chosen by the AIP editors as focused article of frontier research in Virtual Journal of Nanoscale Science &
Technology, 12(9), 2005; **Best paper and Silver “Humies” award. GECCO 2006]
                                                                                                               20
Challenges to Routine Billion-Bit Optimization

 What if you have large nonlinear solver (PDE, ODE, FEM,
 KMC, MD, whatever)?
 Need efficiency enhancement:
   Parallelization: Effective use of computational “space”
   Time continuation: Effective use of computational “time”
   Hybridization: Effective use of global and local searchers
   Evaluation relaxation: Effective use of expensive-accurate
   & cheap-inaccurate evaluations
 Need more powerful solvers
 Need highly efficient implementations

                                                                21
Summary and Conclusions
Parallel and efficient implementation of compact GA.
   Memory and computational efficiency enhancements
   Solved 33 million bit noisy OneMax problem to optimality
   Solved 1.1 billion bit noisy OneMax problem to relaxed, but
   guaranteed convergence
Big optimization is a frontier today:
   Take extant cluster computing
   Mix in robustness, scalability and efficiency lessons
   Integrate into problems.
Nano, bio, and info systems are increasingly complex:
   Call for routine mega/giga-variable optimization
   Need robust, scalable and efficient methods.

                                                                 22

More Related Content

What's hot

R-NSGAII
R-NSGAIIR-NSGAII
R-NSGAII
paskorn
 
Lift-and-Project Cuts in CPLEX 12.5.1
Lift-and-Project Cuts  in CPLEX 12.5.1Lift-and-Project Cuts  in CPLEX 12.5.1
Lift-and-Project Cuts in CPLEX 12.5.1
IBM Decision Optimization
 
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
SKIM
 
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
IDES Editor
 
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
Alkis Vazacopoulos
 
Winner Determination in Combinatorial Reverse Auctions
Winner Determination in Combinatorial Reverse AuctionsWinner Determination in Combinatorial Reverse Auctions
Winner Determination in Combinatorial Reverse Auctions
Shubhashis Shil
 
Profilling Zoo
Profilling ZooProfilling Zoo
Profilling Zoo
ESUG
 
5 psychonomic 2005 1
5 psychonomic 2005 15 psychonomic 2005 1
5 psychonomic 2005 1
Isabault
 

What's hot (8)

R-NSGAII
R-NSGAIIR-NSGAII
R-NSGAII
 
Lift-and-Project Cuts in CPLEX 12.5.1
Lift-and-Project Cuts  in CPLEX 12.5.1Lift-and-Project Cuts  in CPLEX 12.5.1
Lift-and-Project Cuts in CPLEX 12.5.1
 
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
Iterative Multilevel Empirical Bayes (IMEB): An efficient flexible and robust...
 
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
Design of Optimal Linear Phase FIR High Pass Filter using Improved Particle S...
 
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
Phenomenological Decomposition Heuristics for Process Design Synthesis of Oil...
 
Winner Determination in Combinatorial Reverse Auctions
Winner Determination in Combinatorial Reverse AuctionsWinner Determination in Combinatorial Reverse Auctions
Winner Determination in Combinatorial Reverse Auctions
 
Profilling Zoo
Profilling ZooProfilling Zoo
Profilling Zoo
 
5 psychonomic 2005 1
5 psychonomic 2005 15 psychonomic 2005 1
5 psychonomic 2005 1
 

Viewers also liked

iBOA: The Incremental Bayesian Optimization Algorithm
iBOA: The Incremental Bayesian Optimization AlgorithmiBOA: The Incremental Bayesian Optimization Algorithm
iBOA: The Incremental Bayesian Optimization Algorithm
Martin Pelikan
 
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
Martin Pelikan
 
Simplified Runtime Analysis of Estimation of Distribution Algorithms
Simplified Runtime Analysis of Estimation of Distribution AlgorithmsSimplified Runtime Analysis of Estimation of Distribution Algorithms
Simplified Runtime Analysis of Estimation of Distribution Algorithms
Per Kristian Lehre
 
Efficiency Enhancement of Estimation of Distribution Algorithms
Efficiency Enhancement of Estimation of Distribution AlgorithmsEfficiency Enhancement of Estimation of Distribution Algorithms
Efficiency Enhancement of Estimation of Distribution Algorithms
Martin Pelikan
 
Intelligent Bias of Network Structures in the Hierarchical BOA
Intelligent Bias of Network Structures in the Hierarchical BOAIntelligent Bias of Network Structures in the Hierarchical BOA
Intelligent Bias of Network Structures in the Hierarchical BOA
Martin Pelikan
 
Using Previous Models to Bias Structural Learning in the Hierarchical BOA
Using Previous Models to Bias Structural Learning in the Hierarchical BOAUsing Previous Models to Bias Structural Learning in the Hierarchical BOA
Using Previous Models to Bias Structural Learning in the Hierarchical BOA
Martin Pelikan
 
Fitness inheritance in the Bayesian optimization algorithm
Fitness inheritance in the Bayesian optimization algorithmFitness inheritance in the Bayesian optimization algorithm
Fitness inheritance in the Bayesian optimization algorithm
Martin Pelikan
 
Effects of a Deterministic Hill climber on hBOA
Effects of a Deterministic Hill climber on hBOAEffects of a Deterministic Hill climber on hBOA
Effects of a Deterministic Hill climber on hBOA
Martin Pelikan
 
Spurious Dependencies and EDA Scalability
Spurious Dependencies and EDA ScalabilitySpurious Dependencies and EDA Scalability
Spurious Dependencies and EDA Scalability
Martin Pelikan
 
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOATransfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
Martin Pelikan
 
Initial-Population Bias in the Univariate Estimation of Distribution Algorithm
Initial-Population Bias in the Univariate Estimation of Distribution AlgorithmInitial-Population Bias in the Univariate Estimation of Distribution Algorithm
Initial-Population Bias in the Univariate Estimation of Distribution Algorithm
Martin Pelikan
 
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
Martin Pelikan
 
The Bayesian Optimization Algorithm with Substructural Local Search
The Bayesian Optimization Algorithm with Substructural Local SearchThe Bayesian Optimization Algorithm with Substructural Local Search
The Bayesian Optimization Algorithm with Substructural Local Search
Martin Pelikan
 
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin GlassesAnalyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
Martin Pelikan
 
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
Martin Pelikan
 
Estimation of Distribution Algorithms Tutorial
Estimation of Distribution Algorithms TutorialEstimation of Distribution Algorithms Tutorial
Estimation of Distribution Algorithms Tutorial
Martin Pelikan
 

Viewers also liked (16)

iBOA: The Incremental Bayesian Optimization Algorithm
iBOA: The Incremental Bayesian Optimization AlgorithmiBOA: The Incremental Bayesian Optimization Algorithm
iBOA: The Incremental Bayesian Optimization Algorithm
 
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
Analysis of Evolutionary Algorithms on the One-Dimensional Spin Glass with Po...
 
Simplified Runtime Analysis of Estimation of Distribution Algorithms
Simplified Runtime Analysis of Estimation of Distribution AlgorithmsSimplified Runtime Analysis of Estimation of Distribution Algorithms
Simplified Runtime Analysis of Estimation of Distribution Algorithms
 
Efficiency Enhancement of Estimation of Distribution Algorithms
Efficiency Enhancement of Estimation of Distribution AlgorithmsEfficiency Enhancement of Estimation of Distribution Algorithms
Efficiency Enhancement of Estimation of Distribution Algorithms
 
Intelligent Bias of Network Structures in the Hierarchical BOA
Intelligent Bias of Network Structures in the Hierarchical BOAIntelligent Bias of Network Structures in the Hierarchical BOA
Intelligent Bias of Network Structures in the Hierarchical BOA
 
Using Previous Models to Bias Structural Learning in the Hierarchical BOA
Using Previous Models to Bias Structural Learning in the Hierarchical BOAUsing Previous Models to Bias Structural Learning in the Hierarchical BOA
Using Previous Models to Bias Structural Learning in the Hierarchical BOA
 
Fitness inheritance in the Bayesian optimization algorithm
Fitness inheritance in the Bayesian optimization algorithmFitness inheritance in the Bayesian optimization algorithm
Fitness inheritance in the Bayesian optimization algorithm
 
Effects of a Deterministic Hill climber on hBOA
Effects of a Deterministic Hill climber on hBOAEffects of a Deterministic Hill climber on hBOA
Effects of a Deterministic Hill climber on hBOA
 
Spurious Dependencies and EDA Scalability
Spurious Dependencies and EDA ScalabilitySpurious Dependencies and EDA Scalability
Spurious Dependencies and EDA Scalability
 
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOATransfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
Transfer Learning, Soft Distance-Based Bias, and the Hierarchical BOA
 
Initial-Population Bias in the Univariate Estimation of Distribution Algorithm
Initial-Population Bias in the Univariate Estimation of Distribution AlgorithmInitial-Population Bias in the Univariate Estimation of Distribution Algorithm
Initial-Population Bias in the Univariate Estimation of Distribution Algorithm
 
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
Using Problem-Specific Knowledge and Learning from Experience in Estimation o...
 
The Bayesian Optimization Algorithm with Substructural Local Search
The Bayesian Optimization Algorithm with Substructural Local SearchThe Bayesian Optimization Algorithm with Substructural Local Search
The Bayesian Optimization Algorithm with Substructural Local Search
 
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin GlassesAnalyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
Analyzing Probabilistic Models in Hierarchical BOA on Traps and Spin Glasses
 
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
Order Or Not: Does Parallelization of Model Building in hBOA Affect Its Scala...
 
Estimation of Distribution Algorithms Tutorial
Estimation of Distribution Algorithms TutorialEstimation of Distribution Algorithms Tutorial
Estimation of Distribution Algorithms Tutorial
 

Similar to Towards billion bit optimization via parallel estimation of distribution algorithm

11.1. PPT on How to crack ML Competitions all steps explained.pptx
11.1. PPT on How to crack ML Competitions all steps explained.pptx11.1. PPT on How to crack ML Competitions all steps explained.pptx
11.1. PPT on How to crack ML Competitions all steps explained.pptx
hu153574
 
Genetic Algorithms and Genetic Programming for Multiscale Modeling
Genetic Algorithms and Genetic Programming for Multiscale ModelingGenetic Algorithms and Genetic Programming for Multiscale Modeling
Genetic Algorithms and Genetic Programming for Multiscale Modeling
kknsastry
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
byteLAKE
 
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like systemAccelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
Shuai Yuan
 
Graph500
Graph500Graph500
Graph500
Jason Riedy
 
A Performance Study of BDD-Based Model Checking
A Performance Study of BDD-Based Model CheckingA Performance Study of BDD-Based Model Checking
A Performance Study of BDD-Based Model Checking
Olivier Coudert
 
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary pathISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
John Holden
 
Towards quantum machine learning calogero zarbo - meet up
Towards quantum machine learning  calogero zarbo - meet upTowards quantum machine learning  calogero zarbo - meet up
Towards quantum machine learning calogero zarbo - meet up
Deep Learning Italia
 
Tensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with HummingbirdTensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with Hummingbird
Databricks
 
High Performance Pedestrian Detection On TEGRA X1
High Performance Pedestrian Detection On TEGRA X1High Performance Pedestrian Detection On TEGRA X1
High Performance Pedestrian Detection On TEGRA X1
NVIDIA
 
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPUA Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
Carlos Reaño González
 
ICIAM 2019: Reproducible Linear Algebra from Application to Architecture
ICIAM 2019: Reproducible Linear Algebra from Application to ArchitectureICIAM 2019: Reproducible Linear Algebra from Application to Architecture
ICIAM 2019: Reproducible Linear Algebra from Application to Architecture
Jason Riedy
 
The Robust Optimization of Non-Linear Requirements Models
The Robust Optimization of Non-Linear Requirements ModelsThe Robust Optimization of Non-Linear Requirements Models
The Robust Optimization of Non-Linear Requirements Models
gregoryg
 
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "SHow I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
Brandon Liu
 
Manycores for the Masses
Manycores for the MassesManycores for the Masses
Manycores for the Masses
Intel® Software
 
Applying Linear Optimization Using GLPK
Applying Linear Optimization Using GLPKApplying Linear Optimization Using GLPK
Applying Linear Optimization Using GLPK
Jeremy Chen
 
Techniques in Deep Learning
Techniques in Deep LearningTechniques in Deep Learning
Techniques in Deep Learning
Sourya Dey
 
Transcoding of MPEG Compressed Bitstreams: Techniques and ...
Transcoding of MPEG Compressed Bitstreams: Techniques and ...Transcoding of MPEG Compressed Bitstreams: Techniques and ...
Transcoding of MPEG Compressed Bitstreams: Techniques and ...
Videoguy
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMs
SylvainGugger
 
Reproducible Linear Algebra from Application to Architecture
Reproducible Linear Algebra from Application to ArchitectureReproducible Linear Algebra from Application to Architecture
Reproducible Linear Algebra from Application to Architecture
Jason Riedy
 

Similar to Towards billion bit optimization via parallel estimation of distribution algorithm (20)

11.1. PPT on How to crack ML Competitions all steps explained.pptx
11.1. PPT on How to crack ML Competitions all steps explained.pptx11.1. PPT on How to crack ML Competitions all steps explained.pptx
11.1. PPT on How to crack ML Competitions all steps explained.pptx
 
Genetic Algorithms and Genetic Programming for Multiscale Modeling
Genetic Algorithms and Genetic Programming for Multiscale ModelingGenetic Algorithms and Genetic Programming for Multiscale Modeling
Genetic Algorithms and Genetic Programming for Multiscale Modeling
 
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
AI optimizing HPC simulations (presentation from  6th EULAG Workshop)AI optimizing HPC simulations (presentation from  6th EULAG Workshop)
AI optimizing HPC simulations (presentation from 6th EULAG Workshop)
 
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like systemAccelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
Accelerate Reed-Solomon coding for Fault-Tolerance in RAID-like system
 
Graph500
Graph500Graph500
Graph500
 
A Performance Study of BDD-Based Model Checking
A Performance Study of BDD-Based Model CheckingA Performance Study of BDD-Based Model Checking
A Performance Study of BDD-Based Model Checking
 
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary pathISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
ISC Frankfurt 2015: Good, bad and ugly of accelerators and a complementary path
 
Towards quantum machine learning calogero zarbo - meet up
Towards quantum machine learning  calogero zarbo - meet upTowards quantum machine learning  calogero zarbo - meet up
Towards quantum machine learning calogero zarbo - meet up
 
Tensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with HummingbirdTensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with Hummingbird
 
High Performance Pedestrian Detection On TEGRA X1
High Performance Pedestrian Detection On TEGRA X1High Performance Pedestrian Detection On TEGRA X1
High Performance Pedestrian Detection On TEGRA X1
 
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPUA Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
A Study on Atomics-based Integer Sum Reduction in HIP on AMD GPU
 
ICIAM 2019: Reproducible Linear Algebra from Application to Architecture
ICIAM 2019: Reproducible Linear Algebra from Application to ArchitectureICIAM 2019: Reproducible Linear Algebra from Application to Architecture
ICIAM 2019: Reproducible Linear Algebra from Application to Architecture
 
The Robust Optimization of Non-Linear Requirements Models
The Robust Optimization of Non-Linear Requirements ModelsThe Robust Optimization of Non-Linear Requirements Models
The Robust Optimization of Non-Linear Requirements Models
 
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "SHow I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
How I Sped up Complex Matrix-Vector Multiplication: Finding Intel MKL's "S
 
Manycores for the Masses
Manycores for the MassesManycores for the Masses
Manycores for the Masses
 
Applying Linear Optimization Using GLPK
Applying Linear Optimization Using GLPKApplying Linear Optimization Using GLPK
Applying Linear Optimization Using GLPK
 
Techniques in Deep Learning
Techniques in Deep LearningTechniques in Deep Learning
Techniques in Deep Learning
 
Transcoding of MPEG Compressed Bitstreams: Techniques and ...
Transcoding of MPEG Compressed Bitstreams: Techniques and ...Transcoding of MPEG Compressed Bitstreams: Techniques and ...
Transcoding of MPEG Compressed Bitstreams: Techniques and ...
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMs
 
Reproducible Linear Algebra from Application to Architecture
Reproducible Linear Algebra from Application to ArchitectureReproducible Linear Algebra from Application to Architecture
Reproducible Linear Algebra from Application to Architecture
 

More from kknsastry

Population sizing for entropy-based model buliding In genetic algorithms
Population sizing for entropy-based model buliding In genetic algorithms Population sizing for entropy-based model buliding In genetic algorithms
Population sizing for entropy-based model buliding In genetic algorithms
kknsastry
 
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
kknsastry
 
Modeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selectionModeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selection
kknsastry
 
Modeling XCS in class imbalances: Population sizing and parameter settings
Modeling XCS in class imbalances: Population sizing and parameter settingsModeling XCS in class imbalances: Population sizing and parameter settings
Modeling XCS in class imbalances: Population sizing and parameter settings
kknsastry
 
Substructrual surrogates for learning decomposable classification problems: i...
Substructrual surrogates for learning decomposable classification problems: i...Substructrual surrogates for learning decomposable classification problems: i...
Substructrual surrogates for learning decomposable classification problems: i...
kknsastry
 
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
kknsastry
 
Automated alphabet reduction with evolutionary algorithms for protein structu...
Automated alphabet reduction with evolutionary algorithms for protein structu...Automated alphabet reduction with evolutionary algorithms for protein structu...
Automated alphabet reduction with evolutionary algorithms for protein structu...
kknsastry
 
Analyzing probabilistic models in hierarchical BOA on traps and spin glasses
Analyzing probabilistic models in hierarchical BOA on traps and spin glassesAnalyzing probabilistic models in hierarchical BOA on traps and spin glasses
Analyzing probabilistic models in hierarchical BOA on traps and spin glasses
kknsastry
 
Modeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selectionModeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selection
kknsastry
 
Modeling XCS in class imbalances: Population size and parameter settings
Modeling XCS in class imbalances: Population size and parameter settingsModeling XCS in class imbalances: Population size and parameter settings
Modeling XCS in class imbalances: Population size and parameter settings
kknsastry
 
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
kknsastry
 
On Extended Compact Genetic Algorithm
On Extended Compact Genetic AlgorithmOn Extended Compact Genetic Algorithm
On Extended Compact Genetic Algorithm
kknsastry
 
Silicon Cluster Optimization Using Extended Compact Genetic Algorithm
Silicon Cluster Optimization Using Extended Compact Genetic AlgorithmSilicon Cluster Optimization Using Extended Compact Genetic Algorithm
Silicon Cluster Optimization Using Extended Compact Genetic Algorithm
kknsastry
 
A Practical Schema Theorem for Genetic Algorithm Design and Tuning
A Practical Schema Theorem for Genetic Algorithm Design and TuningA Practical Schema Theorem for Genetic Algorithm Design and Tuning
A Practical Schema Theorem for Genetic Algorithm Design and Tuning
kknsastry
 
On the Supply of Building Blocks
On the Supply of Building BlocksOn the Supply of Building Blocks
On the Supply of Building Blocks
kknsastry
 
Don't Evaluate, Inherit
Don't Evaluate, InheritDon't Evaluate, Inherit
Don't Evaluate, Inherit
kknsastry
 
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
kknsastry
 
Modeling Tournament Selection with Replacement Using Apparent Added Noise
Modeling Tournament Selection with Replacement Using Apparent Added NoiseModeling Tournament Selection with Replacement Using Apparent Added Noise
Modeling Tournament Selection with Replacement Using Apparent Added Noise
kknsastry
 
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
kknsastry
 
Analysis of Mixing in Genetic Algorithms: A Survey
Analysis of Mixing in Genetic Algorithms: A SurveyAnalysis of Mixing in Genetic Algorithms: A Survey
Analysis of Mixing in Genetic Algorithms: A Survey
kknsastry
 

More from kknsastry (20)

Population sizing for entropy-based model buliding In genetic algorithms
Population sizing for entropy-based model buliding In genetic algorithms Population sizing for entropy-based model buliding In genetic algorithms
Population sizing for entropy-based model buliding In genetic algorithms
 
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
 
Modeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selectionModeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selection
 
Modeling XCS in class imbalances: Population sizing and parameter settings
Modeling XCS in class imbalances: Population sizing and parameter settingsModeling XCS in class imbalances: Population sizing and parameter settings
Modeling XCS in class imbalances: Population sizing and parameter settings
 
Substructrual surrogates for learning decomposable classification problems: i...
Substructrual surrogates for learning decomposable classification problems: i...Substructrual surrogates for learning decomposable classification problems: i...
Substructrual surrogates for learning decomposable classification problems: i...
 
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
Let's get ready to rumble redux: Crossover versus mutation head to head on ex...
 
Automated alphabet reduction with evolutionary algorithms for protein structu...
Automated alphabet reduction with evolutionary algorithms for protein structu...Automated alphabet reduction with evolutionary algorithms for protein structu...
Automated alphabet reduction with evolutionary algorithms for protein structu...
 
Analyzing probabilistic models in hierarchical BOA on traps and spin glasses
Analyzing probabilistic models in hierarchical BOA on traps and spin glassesAnalyzing probabilistic models in hierarchical BOA on traps and spin glasses
Analyzing probabilistic models in hierarchical BOA on traps and spin glasses
 
Modeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selectionModeling selection pressure in XCS for proportionate and tournament selection
Modeling selection pressure in XCS for proportionate and tournament selection
 
Modeling XCS in class imbalances: Population size and parameter settings
Modeling XCS in class imbalances: Population size and parameter settingsModeling XCS in class imbalances: Population size and parameter settings
Modeling XCS in class imbalances: Population size and parameter settings
 
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
Fast and accurate reaction dynamics via multiobjective genetic algorithm opti...
 
On Extended Compact Genetic Algorithm
On Extended Compact Genetic AlgorithmOn Extended Compact Genetic Algorithm
On Extended Compact Genetic Algorithm
 
Silicon Cluster Optimization Using Extended Compact Genetic Algorithm
Silicon Cluster Optimization Using Extended Compact Genetic AlgorithmSilicon Cluster Optimization Using Extended Compact Genetic Algorithm
Silicon Cluster Optimization Using Extended Compact Genetic Algorithm
 
A Practical Schema Theorem for Genetic Algorithm Design and Tuning
A Practical Schema Theorem for Genetic Algorithm Design and TuningA Practical Schema Theorem for Genetic Algorithm Design and Tuning
A Practical Schema Theorem for Genetic Algorithm Design and Tuning
 
On the Supply of Building Blocks
On the Supply of Building BlocksOn the Supply of Building Blocks
On the Supply of Building Blocks
 
Don't Evaluate, Inherit
Don't Evaluate, InheritDon't Evaluate, Inherit
Don't Evaluate, Inherit
 
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
Efficient Cluster Optimization Using A Hybrid Extended Compact Genetic Algori...
 
Modeling Tournament Selection with Replacement Using Apparent Added Noise
Modeling Tournament Selection with Replacement Using Apparent Added NoiseModeling Tournament Selection with Replacement Using Apparent Added Noise
Modeling Tournament Selection with Replacement Using Apparent Added Noise
 
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
Evaluation Relaxation as an Efficiency-Enhancement Technique: Handling Varian...
 
Analysis of Mixing in Genetic Algorithms: A Survey
Analysis of Mixing in Genetic Algorithms: A SurveyAnalysis of Mixing in Genetic Algorithms: A Survey
Analysis of Mixing in Genetic Algorithms: A Survey
 

Recently uploaded

Structural Design Process: Step-by-Step Guide for Buildings
Structural Design Process: Step-by-Step Guide for BuildingsStructural Design Process: Step-by-Step Guide for Buildings
Structural Design Process: Step-by-Step Guide for Buildings
Chandresh Chudasama
 
Understanding User Needs and Satisfying Them
Understanding User Needs and Satisfying ThemUnderstanding User Needs and Satisfying Them
Understanding User Needs and Satisfying Them
Aggregage
 
buy old yahoo accounts buy yahoo accounts
buy old yahoo accounts buy yahoo accountsbuy old yahoo accounts buy yahoo accounts
buy old yahoo accounts buy yahoo accounts
Susan Laney
 
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
ABHILASH DUTTA
 
Best Forex Brokers Comparison in INDIA 2024
Best Forex Brokers Comparison in INDIA 2024Best Forex Brokers Comparison in INDIA 2024
Best Forex Brokers Comparison in INDIA 2024
Top Forex Brokers Review
 
Company Valuation webinar series - Tuesday, 4 June 2024
Company Valuation webinar series - Tuesday, 4 June 2024Company Valuation webinar series - Tuesday, 4 June 2024
Company Valuation webinar series - Tuesday, 4 June 2024
FelixPerez547899
 
Creative Web Design Company in Singapore
Creative Web Design Company in SingaporeCreative Web Design Company in Singapore
Creative Web Design Company in Singapore
techboxsqauremedia
 
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Lviv Startup Club
 
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel ChartSatta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
➒➌➎➏➑➐➋➑➐➐Dpboss Matka Guessing Satta Matka Kalyan Chart Indian Matka
 
Mastering B2B Payments Webinar from BlueSnap
Mastering B2B Payments Webinar from BlueSnapMastering B2B Payments Webinar from BlueSnap
Mastering B2B Payments Webinar from BlueSnap
Norma Mushkat Gaffin
 
2022 Vintage Roman Numerals Men Rings
2022 Vintage Roman  Numerals  Men  Rings2022 Vintage Roman  Numerals  Men  Rings
2022 Vintage Roman Numerals Men Rings
aragme
 
Authentically Social by Corey Perlman - EO Puerto Rico
Authentically Social by Corey Perlman - EO Puerto RicoAuthentically Social by Corey Perlman - EO Puerto Rico
Authentically Social by Corey Perlman - EO Puerto Rico
Corey Perlman, Social Media Speaker and Consultant
 
The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...
Adam Smith
 
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
SOFTTECHHUB
 
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challengesEvent Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
Holger Mueller
 
Industrial Tech SW: Category Renewal and Creation
Industrial Tech SW:  Category Renewal and CreationIndustrial Tech SW:  Category Renewal and Creation
Industrial Tech SW: Category Renewal and Creation
Christian Dahlen
 
LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024
Lital Barkan
 
Business storytelling: key ingredients to a story
Business storytelling: key ingredients to a storyBusiness storytelling: key ingredients to a story
Business storytelling: key ingredients to a story
Alexandra Fulford
 
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdfThe 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
thesiliconleaders
 
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
my Pandit
 

Recently uploaded (20)

Structural Design Process: Step-by-Step Guide for Buildings
Structural Design Process: Step-by-Step Guide for BuildingsStructural Design Process: Step-by-Step Guide for Buildings
Structural Design Process: Step-by-Step Guide for Buildings
 
Understanding User Needs and Satisfying Them
Understanding User Needs and Satisfying ThemUnderstanding User Needs and Satisfying Them
Understanding User Needs and Satisfying Them
 
buy old yahoo accounts buy yahoo accounts
buy old yahoo accounts buy yahoo accountsbuy old yahoo accounts buy yahoo accounts
buy old yahoo accounts buy yahoo accounts
 
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
The Evolution and Impact of OTT Platforms: A Deep Dive into the Future of Ent...
 
Best Forex Brokers Comparison in INDIA 2024
Best Forex Brokers Comparison in INDIA 2024Best Forex Brokers Comparison in INDIA 2024
Best Forex Brokers Comparison in INDIA 2024
 
Company Valuation webinar series - Tuesday, 4 June 2024
Company Valuation webinar series - Tuesday, 4 June 2024Company Valuation webinar series - Tuesday, 4 June 2024
Company Valuation webinar series - Tuesday, 4 June 2024
 
Creative Web Design Company in Singapore
Creative Web Design Company in SingaporeCreative Web Design Company in Singapore
Creative Web Design Company in Singapore
 
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
Evgen Osmak: Methods of key project parameters estimation: from the shaman-in...
 
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel ChartSatta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
Satta Matka Dpboss Matka Guessing Kalyan Chart Indian Matka Kalyan panel Chart
 
Mastering B2B Payments Webinar from BlueSnap
Mastering B2B Payments Webinar from BlueSnapMastering B2B Payments Webinar from BlueSnap
Mastering B2B Payments Webinar from BlueSnap
 
2022 Vintage Roman Numerals Men Rings
2022 Vintage Roman  Numerals  Men  Rings2022 Vintage Roman  Numerals  Men  Rings
2022 Vintage Roman Numerals Men Rings
 
Authentically Social by Corey Perlman - EO Puerto Rico
Authentically Social by Corey Perlman - EO Puerto RicoAuthentically Social by Corey Perlman - EO Puerto Rico
Authentically Social by Corey Perlman - EO Puerto Rico
 
The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...The Influence of Marketing Strategy and Market Competition on Business Perfor...
The Influence of Marketing Strategy and Market Competition on Business Perfor...
 
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
Hamster Kombat' Telegram Game Surpasses 100 Million Players—Token Release Sch...
 
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challengesEvent Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
Event Report - SAP Sapphire 2024 Orlando - lots of innovation and old challenges
 
Industrial Tech SW: Category Renewal and Creation
Industrial Tech SW:  Category Renewal and CreationIndustrial Tech SW:  Category Renewal and Creation
Industrial Tech SW: Category Renewal and Creation
 
LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024LA HUG - Video Testimonials with Chynna Morgan - June 2024
LA HUG - Video Testimonials with Chynna Morgan - June 2024
 
Business storytelling: key ingredients to a story
Business storytelling: key ingredients to a storyBusiness storytelling: key ingredients to a story
Business storytelling: key ingredients to a story
 
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdfThe 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
The 10 Most Influential Leaders Guiding Corporate Evolution, 2024.pdf
 
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
Taurus Zodiac Sign: Unveiling the Traits, Dates, and Horoscope Insights of th...
 

Towards billion bit optimization via parallel estimation of distribution algorithm

  • 1. Towards Billion Bit Optimization via Efficient Estimation of Distribution Algorithms Kumara Sastry1,2 David E. Goldberg1, Xavier Llorà1,3 1Illinois Genetic Algorithms Laboratory (IlliGAL) 2Materials Computation Center (MCC) 3National Center for Super Computing Applications (NCSA) University of Illinois at Urbana-Champaign, Urbana, IL 61801 ksastry@uiuc.edu, deg@uiuc.edu, xllora@uiuc.edu http://www.illigal.uiuc.edu Supported by AFOSR FA9550-06-1-0096 and NSF DMR 03-25939. Computational results were obtained using CSE’s Turing cluster.
  • 2. Billion-Bit Optimization? Strides w/ genetic algorithm (GA) theory/practice. Solving large, hard problems in principled way. Moving to practice in important problem domains. Still GA boobirds claim: (1) no theory, (2) too slow, and (3) just voodoo. How demonstrate results achieved so far in dramatic way? DEG lunch questions: A million? Sure. A billion? Maybe. Naïve GA approach/implementation goes nowhere: ~100 terabytes memory for population storage. ~272 random number calls. 2
  • 3. Roadmap Motivation Robust, scalable, and efficient GA designs Toward billion-variable optimization Theory Keys Implementation Keys Efficiency Keys Results Why this matters in practice? Challenges to using this in real-world. Summary and Conclusions 3
  • 4. Three Os and Million/Billion Decisions The Os all have many decisions to make: Nano, Bio, and Info Modern systems increasingly complex: ~105 parts in a modern automobile ~107 parts in commercial jetliner. Increased complexity increases appetite for large optimization. Will be driven toward routine million/billion variable problems. “We get the warhead and then hold the world ransom for... 1 MILLION dollars!” 4
  • 5. Competent and Efficient GAs Robust, scalable and efficient GA designs available. Competence: Solve hard problems quickly, reliably, and accurately (Intractable to tractable). Efficiency: Develop speedup procedures (tractability to practicality). Principled design: [Goldberg, 2002] Relax rigor, emphasize scalability/quality. Use problem decomposition. Use facetwise models, and patchquilt integration using dimensional analysis. Test algorithms on adversarial problems 5
  • 6. Aiming for a Billion Theory & algorithms in place. Focus on key theory, implementation, & efficiency enhancements. Theory keys: Problem difficulty. Parallelism. Implementation key: compact GA. Efficiency keys: Various speedup. Memory savings. Results on a billion-variable noisy OneMax. 6
  • 7. Theory Key 1: Master-Slave Linear Speedup Speed-up: Max speed-up at Near linear speed-up until [Cantu-Paz & Goldberg, 1997; Cantú-Paz, 2000] 7
  • 8. Theory Key 2: Noise Covers Most Problems Adversarial problem design [Goldberg, 2002] Fluctuating R P Noise Deception Scaling Blind noisy OneMax 8
  • 9. Implementation Key: Compact GA Simplest probabilistic model building GA [Harik, Lobo & Goldberg, 1997; Baluja, 1994; Mühlenbein & Paaß, 1996] Represent population by probability vector Probability that ith bit is 1 Replace recombination with probabilistic sampling Selectionist scheme New population evolution through probability updates Equivalent to GA with steady-state tournament selection and uniform crossover 9
  • 10. Compact Genetic Algorithm (cGA) Random initialization: Set probabilities to 0.5 Model Sampling: Generate two candidate solutions by sampling the probability vector Evaluation: Evaluate the fitness of two sampled solutions Selection: Select the best among the sampled solutions Probabilistic model update: Increase the proportion of winning alleles by 1/n 10
  • 11. Parallel cGA Architecture Processor #1 Processor #2 Processor #np Sample bits 1- l/np Sample bits l/np+1- 2l/np Sample bits (np-1)l/np+1- l Collect partial sampled solutions and combine Parallel fitness evaluation of sampled solutions Broadcast fitness values of sampled solutions Select best individual Select best individual Select best individual Update probabilities Update probabilities Update probabilities 11
  • 12. cGA is Memory Efficient: O(l) vs. O(l1.5) Simple GA: Compact GA: Frequencies instead of probabilities (4 bytes) Parallelization reduces memory per processor by factor of np Orders of magnitude memory savings via efficient GA Example: ~32 MB per processor on a modest 128 processors for billion-bit optimization 12
  • 13. Vectorization Yields Speedup of 4 Vectorize costly code segments with AltiVec/SSE2 Generate 4 random numbers at a time Sample 4 bits at a time Update 4 probabilities at a time SIMD instruction set allows vector operations on 128-bit registers Equivalent to 4 processors per processor 13
  • 14. Other Efficiencies Yield Speedup of 15 Bitwise operations Limited floating-point operations Inline functions Avoid using mod and division operations Precomputing bit sums and indexing Parallel, vectorized, and efficient GA: Memory scales as Θ(l/np); Speedup scales as 60np ~32 MB memory, and ~104 speedup with 128 processors Solves 65,536-bit noisy OneMax problem in ~45 minutes on a 3GHz PC. 14
  • 15. Experimental Procedure 128 – 256 processor partition of 1280-processor Apple G5 Xserve Population was doubled till cGA converged to at least l-1 out of l bits set to optimal values For l > 223; Population size fixed according to theory. Number of independent runs l ≤ 218 (262,144): 50 l ≤ 225 (33, 554, 432): 10 l > 225 (33, 554, 432): 1 Compare cGA performance with Sequential hillclimber (sHC) Random hillclimber (rHC) 15
  • 16. Compact GA Population Sizing Noise-to-fitness variance ratio Error tolerance # Components (# BBs) Signal-to-Noise ratio # Competing sub-components Additive Gaussian noise with variance σ2N Population sizing scales: O(l0.5 log l) [Harik, et al, 1997] 16
  • 17. Compact GA Convergence Time Problem size (m·k ) Selection Intensity Convergence time scales: O(m0.5) GA scales as: O(m log m) [Miller & Goldberg, 1995; Goldberg, 2002; Sastry & Goldberg, 2002] 17
  • 19. EDA Solves Billion-Bit Noisy OneMax GA scales Θ(l·logl·(1+σ2N/σ2f)) Solved 33 million (225) bit problem to optimality. Solved 1.1 billion (230) bit problem with relaxed, but guaranteed convergence 19
  • 20. Do Problems Like This Matter? Yes, for three reasons: Many GAs no more sophisticated than cGA. Inclusion of noise was important because it covers an important facet of difficulty. Know how to handle deception and other problems through EDAs like hBOA. Compact GA-like algorithms can solve tough problems: Material science [Sastry et al, 2004; Sastry et al, 2005]* Chemistry [Sastry et al, 2006]**. Complex versions of these kinds of problems need million/billion-bit optimization. *chosen by the AIP editors as focused article of frontier research in Virtual Journal of Nanoscale Science & Technology, 12(9), 2005; **Best paper and Silver “Humies” award. GECCO 2006] 20
  • 21. Challenges to Routine Billion-Bit Optimization What if you have large nonlinear solver (PDE, ODE, FEM, KMC, MD, whatever)? Need efficiency enhancement: Parallelization: Effective use of computational “space” Time continuation: Effective use of computational “time” Hybridization: Effective use of global and local searchers Evaluation relaxation: Effective use of expensive-accurate & cheap-inaccurate evaluations Need more powerful solvers Need highly efficient implementations 21
  • 22. Summary and Conclusions Parallel and efficient implementation of compact GA. Memory and computational efficiency enhancements Solved 33 million bit noisy OneMax problem to optimality Solved 1.1 billion bit noisy OneMax problem to relaxed, but guaranteed convergence Big optimization is a frontier today: Take extant cluster computing Mix in robustness, scalability and efficiency lessons Integrate into problems. Nano, bio, and info systems are increasingly complex: Call for routine mega/giga-variable optimization Need robust, scalable and efficient methods. 22