SlideShare a Scribd company logo
1 of 17
Download to read offline
THE FORWARD-BACKWARD SPLITTING
ALGORITHM WITHOUT COCOERCIVITY?
Saverio Salzo
Istituto Italiano di Tecnologia
Genova, Italy
Workshop on Operator Splitting Methods in Data Analysis
Samsi, Durham, NC, March, 21-23, 2018
is a real Hilbert space with scalar product
is maximal monotone
is -cocoercive, that is
ZEROS OF SUM OF MONOTONE OPERATORS
The problem
H h· , ·i
A: H ! 2H
B : H ! H
find ¯x 2 H s.t. 0 2 A(¯x) + B(¯x)
kB(x) B(y)k2
 hx y, B(x) B(y)i
is a real Hilbert space with scalar product
is maximal monotone if is

proper, convex, and lower semicontinuous.
is -cocoercive iff it is -Lipschitz
continuous.
MINIMIZATION OF SUM OF FUNCTIONS
The problem
h· , ·i
find ¯x 2 H s.t. 0 2 @f(¯x) + rg(¯x)
@f : H ! 2H f : H ! ] 1, +1]
rg: H ! H (1/ )
H
is a real Hilbert space with scalar product
is maximal monotone if is

nonempty, closed, and convex.
is -cocoercive.
VARIATIONAL INEQUALITIES
The problem
find ¯x 2 C s.t. 8 x 2 C h¯x x, B¯xi  0
A = @iC = NC C ⇢ H
B : H ! H
h· , ·iH
THE FORWARD-BACKWARD SPLITTING
(Mercier ’79)
The algorithm
if and , then

xk+1 = J kA(xk kB(xk))
Convergence: if k < 2
xk * ¯x 2 zer(A + B)
A = @f B = rg (f + g)(xk) inf(f + g) = o(1/k)
Cocoercivity of is a fundamental assumption!B
minimize
x2Rd
+
DKL(b, Ax) + ⌧kxk1
minimize
x2Rd
1
p
kAx bkp
p + ⌧kxk1 (p > 1)
minimize
w2Rd
nX
i=1
L(yi, hw, xii) +
⌧
p
kwkp
p (1 < p < 2)
When cocoercivity is an issue
minimize
x2Rd
1
p
kAx bkp
p + ⌧kxk1 (p > 1)
minimize
↵2Rn
1
q
kX⇤
↵kq
q +
1
⌧
nX
i=1
L⇤
(yi, ⌧↵i) (q > 2)
When cocoercivity is an issue
minimize
x2Rd
+
DKL(b, Ax) + ⌧kxk1
TSENG’S SPLITTING
(Tseng ’00)
is maximal monotone
is uniformly continuous on bounded sets
is chosen by the backtracking procedure: let
B : H ! H
k
kB(yk) B(xk)k 
k
kyk xkk
2 ]0, 1[
The algorithm converges if
A: H ! 2H
yk = J kA(xk kB(xk))
xk+1 = yk kB(yk) + kB(xk)
Strategies without cocoercivity
, is proper, convex, and lsc
is uniformly continuous on bounded sets.
is determined by backtracking line search procedures
(a priori choices are not possible anymore).
THE FORWARD-BACKWARD SPLITTING 

FOR MINIMIZATION PROBLEMS
xk+1 = J kA(xk kB(xk))
B = rg
A = @f f : H ! ] 1, +1]
k
The algorithm converges if
S. Salzo, The variable metric forward-backward splitting algorithm under mild
differentiability assumptions. SIOPT 2017.
Strategies without cocoercivity
BACKTRACKING LINE SEARCHES
L1)
L2)
L3)
We considered three possible inequalities: let
krg(xk+1) rg(xk)k 
k
kxk+1 xkk
g(xk+1) g(xk) hxk+1 xk, rg(xk)i 
k
kxk+1 xkk2
(f + g)(xk+1) (f + g)(xk)
 (1 ) f(xk+1) f(xk) + hxk+1 xk, rg(xk)i
2 ]0, 1[
L1) L2) L3)
L1) is not quite appropriate for FB algorithm since it leads
to halve the step-sizes w.r.t. L2) and L3)
=) =)
Strategies without cocoercivity
FBA FBFA
They work under exactly the same
assumptions!
MINIMIZATION PROBLEMS
Strategies without cocoercivity
THE PROBLEM: DEVISE AN APPROPRIATE
BACKTRACKING LINESEARCH THAT REPLACES
THE COCOERCIVITY
What about the FB algorithm for 

monotone operators?
Removing cocoercivity
Where does cocoercivity enter?
kxk+1 ¯xk2
 kxk ¯xk2
kxk+1 xkk2
2 khxk ¯x, B(xk) B(¯x)i
2 khxk+1 xk, B(xk) B(¯x)i
= kxk ¯xk2
k(2 k)kB(xk) B(¯x)k2
k(xk+1 xk) k(B(xk) B(¯x))k2
FB ALGORITHM FOR MONOTONE OPERATORS
Where does cocoercivity enter?
FB ALGORITHM FOR MINIMIZATION PROBLEMS
kxk+1 xk2
 kxk xk2
kxk+1 xkk2
+ 2 k (f + g)(x) (f + g)(xk)
2 k g(xk+1) g(xk) + hxk+1 xk, rg(xk)i
 kxk xk2
+ (2 1)kxk+1 xkk2
+ 2 k (f + g)(x) (f + g)(xk)
+ 2 k (f + g)(xk) (f + g)(xk+1)
Possible strategies
only value of B?







would not work!
the values of function (to be determined), that hopefully
should decrease along the iterations?
k
kB(xk+1) B(xk)k2
 hB(xk+1) B(xk), xk+1 xki
The inequality should involve:
,
Possible strategies
PRIMAL DUAL ALGORITHMS
min
x2H
g(x) + h(Lx)
✓
0
0
◆
2 A
✓
¯x
¯v
◆
+ B
✓
¯x
¯v
◆
A
✓
x
v
◆
=
✓
L⇤
v
@h⇤
(v) Lx
◆
B
✓
x
v
◆
=
✓
rg(x)
0
◆
is convex and continuously differentiable.g: H ! R
(Combettes-Pesquet ’12, Condat ’13, Vu ’13)
Should backtracking involve the duality gap function?
Thank you!

More Related Content

What's hot

Meta-learning and the ELBO
Meta-learning and the ELBOMeta-learning and the ELBO
Meta-learning and the ELBOYoonho Lee
 
New Insights and Perspectives on the Natural Gradient Method
New Insights and Perspectives on the Natural Gradient MethodNew Insights and Perspectives on the Natural Gradient Method
New Insights and Perspectives on the Natural Gradient MethodYoonho Lee
 
Convergence methods for approximated reciprocal and reciprocal-square-root
Convergence methods for approximated reciprocal and reciprocal-square-rootConvergence methods for approximated reciprocal and reciprocal-square-root
Convergence methods for approximated reciprocal and reciprocal-square-rootKeigo Nitadori
 
Time and space complexity
Time and space complexityTime and space complexity
Time and space complexityAnkit Katiyar
 
2021 preTEST4A Vector Calculus
2021 preTEST4A Vector Calculus2021 preTEST4A Vector Calculus
2021 preTEST4A Vector CalculusA Jorge Garcia
 
Optimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
Optimal Budget Allocation: Theoretical Guarantee and Efficient AlgorithmOptimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
Optimal Budget Allocation: Theoretical Guarantee and Efficient AlgorithmTasuku Soma
 
pradeepbishtLecture13 div conq
pradeepbishtLecture13 div conqpradeepbishtLecture13 div conq
pradeepbishtLecture13 div conqPradeep Bisht
 
Quasi-Majority Functional Voting on Expander Graphs
Quasi-Majority Functional Voting on Expander GraphsQuasi-Majority Functional Voting on Expander Graphs
Quasi-Majority Functional Voting on Expander GraphsNobutaka Shimizu
 
2021 preTEST5A Final Review Packet!
2021 preTEST5A Final Review Packet!2021 preTEST5A Final Review Packet!
2021 preTEST5A Final Review Packet!A Jorge Garcia
 
Estimating structured vector autoregressive models
Estimating structured vector autoregressive modelsEstimating structured vector autoregressive models
Estimating structured vector autoregressive modelsAkira Tanimoto
 
Asymptotic Notations
Asymptotic NotationsAsymptotic Notations
Asymptotic NotationsRishabh Soni
 
Theory of automata and formal languages Unit 4
Theory of automata and formal languages Unit 4Theory of automata and formal languages Unit 4
Theory of automata and formal languages Unit 4Abhimanyu Mishra
 
4.7 inverse functions.ppt worked
4.7   inverse functions.ppt worked4.7   inverse functions.ppt worked
4.7 inverse functions.ppt workedJonna Ramsey
 
April 2015 APS presentation
April 2015 APS presentationApril 2015 APS presentation
April 2015 APS presentationAdam Getchell
 
Lec 5 asymptotic notations and recurrences
Lec 5 asymptotic notations and recurrencesLec 5 asymptotic notations and recurrences
Lec 5 asymptotic notations and recurrencesAnkita Karia
 
10.1.1.474.2861
10.1.1.474.286110.1.1.474.2861
10.1.1.474.2861pkavitha
 

What's hot (20)

Meta-learning and the ELBO
Meta-learning and the ELBOMeta-learning and the ELBO
Meta-learning and the ELBO
 
New Insights and Perspectives on the Natural Gradient Method
New Insights and Perspectives on the Natural Gradient MethodNew Insights and Perspectives on the Natural Gradient Method
New Insights and Perspectives on the Natural Gradient Method
 
Convergence methods for approximated reciprocal and reciprocal-square-root
Convergence methods for approximated reciprocal and reciprocal-square-rootConvergence methods for approximated reciprocal and reciprocal-square-root
Convergence methods for approximated reciprocal and reciprocal-square-root
 
Time and space complexity
Time and space complexityTime and space complexity
Time and space complexity
 
2021 preTEST4A Vector Calculus
2021 preTEST4A Vector Calculus2021 preTEST4A Vector Calculus
2021 preTEST4A Vector Calculus
 
Optimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
Optimal Budget Allocation: Theoretical Guarantee and Efficient AlgorithmOptimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
Optimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm
 
pradeepbishtLecture13 div conq
pradeepbishtLecture13 div conqpradeepbishtLecture13 div conq
pradeepbishtLecture13 div conq
 
SPSF03 - Numerical Integrations
SPSF03 - Numerical IntegrationsSPSF03 - Numerical Integrations
SPSF03 - Numerical Integrations
 
Quasi-Majority Functional Voting on Expander Graphs
Quasi-Majority Functional Voting on Expander GraphsQuasi-Majority Functional Voting on Expander Graphs
Quasi-Majority Functional Voting on Expander Graphs
 
2021 preTEST5A Final Review Packet!
2021 preTEST5A Final Review Packet!2021 preTEST5A Final Review Packet!
2021 preTEST5A Final Review Packet!
 
1988 FRQs AP Calculus
1988 FRQs AP Calculus1988 FRQs AP Calculus
1988 FRQs AP Calculus
 
yaron_eurika_
yaron_eurika_yaron_eurika_
yaron_eurika_
 
Estimating structured vector autoregressive models
Estimating structured vector autoregressive modelsEstimating structured vector autoregressive models
Estimating structured vector autoregressive models
 
Computational Complexity
Computational ComplexityComputational Complexity
Computational Complexity
 
Asymptotic Notations
Asymptotic NotationsAsymptotic Notations
Asymptotic Notations
 
Theory of automata and formal languages Unit 4
Theory of automata and formal languages Unit 4Theory of automata and formal languages Unit 4
Theory of automata and formal languages Unit 4
 
4.7 inverse functions.ppt worked
4.7   inverse functions.ppt worked4.7   inverse functions.ppt worked
4.7 inverse functions.ppt worked
 
April 2015 APS presentation
April 2015 APS presentationApril 2015 APS presentation
April 2015 APS presentation
 
Lec 5 asymptotic notations and recurrences
Lec 5 asymptotic notations and recurrencesLec 5 asymptotic notations and recurrences
Lec 5 asymptotic notations and recurrences
 
10.1.1.474.2861
10.1.1.474.286110.1.1.474.2861
10.1.1.474.2861
 

Similar to QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm without Cocoercivity - Saverio Salzo, Mar 22, 2018

Chapter 2-2.pdf
Chapter 2-2.pdfChapter 2-2.pdf
Chapter 2-2.pdfrziguiala
 
Convex Optimization Modelling with CVXOPT
Convex Optimization Modelling with CVXOPTConvex Optimization Modelling with CVXOPT
Convex Optimization Modelling with CVXOPTandrewmart11
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Tomoya Murata
 
Calculus of variations
Calculus of variationsCalculus of variations
Calculus of variationsSolo Hermelin
 
Lp and ip programming cp 9
Lp and ip programming cp 9Lp and ip programming cp 9
Lp and ip programming cp 9M S Prasad
 
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997JOAQUIN REA
 
ISI MSQE Entrance Question Paper (2008)
ISI MSQE Entrance Question Paper (2008)ISI MSQE Entrance Question Paper (2008)
ISI MSQE Entrance Question Paper (2008)CrackDSE
 
Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningSungbin Lim
 
Alternating direction
Alternating directionAlternating direction
Alternating directionDerek Pang
 
June Overview SN5 Math
June Overview SN5 MathJune Overview SN5 Math
June Overview SN5 Mathamcsquared
 
QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017Fred J. Hickernell
 
ISI MSQE Entrance Question Paper (2010)
ISI MSQE Entrance Question Paper (2010)ISI MSQE Entrance Question Paper (2010)
ISI MSQE Entrance Question Paper (2010)CrackDSE
 
NIPS2010: optimization algorithms in machine learning
NIPS2010: optimization algorithms in machine learningNIPS2010: optimization algorithms in machine learning
NIPS2010: optimization algorithms in machine learningzukun
 

Similar to QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm without Cocoercivity - Saverio Salzo, Mar 22, 2018 (20)

QMC: Operator Splitting Workshop, A New (More Intuitive?) Interpretation of I...
QMC: Operator Splitting Workshop, A New (More Intuitive?) Interpretation of I...QMC: Operator Splitting Workshop, A New (More Intuitive?) Interpretation of I...
QMC: Operator Splitting Workshop, A New (More Intuitive?) Interpretation of I...
 
chapter3.ppt
chapter3.pptchapter3.ppt
chapter3.ppt
 
Chapter 2-2.pdf
Chapter 2-2.pdfChapter 2-2.pdf
Chapter 2-2.pdf
 
Convex Optimization Modelling with CVXOPT
Convex Optimization Modelling with CVXOPTConvex Optimization Modelling with CVXOPT
Convex Optimization Modelling with CVXOPT
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
 
Calculus of variations
Calculus of variationsCalculus of variations
Calculus of variations
 
Lp and ip programming cp 9
Lp and ip programming cp 9Lp and ip programming cp 9
Lp and ip programming cp 9
 
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997
Computer Controlled Systems (solutions manual). Astrom. 3rd edition 1997
 
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
QMC: Operator Splitting Workshop, A Splitting Method for Nonsmooth Nonconvex ...
 
ISI MSQE Entrance Question Paper (2008)
ISI MSQE Entrance Question Paper (2008)ISI MSQE Entrance Question Paper (2008)
ISI MSQE Entrance Question Paper (2008)
 
Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep Learning
 
Alternating direction
Alternating directionAlternating direction
Alternating direction
 
June Overview SN5 Math
June Overview SN5 MathJune Overview SN5 Math
June Overview SN5 Math
 
QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017QMC Error SAMSI Tutorial Aug 2017
QMC Error SAMSI Tutorial Aug 2017
 
QMC: Operator Splitting Workshop, Boundedness of the Sequence if Iterates Gen...
QMC: Operator Splitting Workshop, Boundedness of the Sequence if Iterates Gen...QMC: Operator Splitting Workshop, Boundedness of the Sequence if Iterates Gen...
QMC: Operator Splitting Workshop, Boundedness of the Sequence if Iterates Gen...
 
YSC 2013
YSC 2013YSC 2013
YSC 2013
 
ISI MSQE Entrance Question Paper (2010)
ISI MSQE Entrance Question Paper (2010)ISI MSQE Entrance Question Paper (2010)
ISI MSQE Entrance Question Paper (2010)
 
NIPS2010: optimization algorithms in machine learning
NIPS2010: optimization algorithms in machine learningNIPS2010: optimization algorithms in machine learning
NIPS2010: optimization algorithms in machine learning
 
cyclic_code.pdf
cyclic_code.pdfcyclic_code.pdf
cyclic_code.pdf
 
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
Program on Quasi-Monte Carlo and High-Dimensional Sampling Methods for Applie...
 

More from The Statistical and Applied Mathematical Sciences Institute

More from The Statistical and Applied Mathematical Sciences Institute (20)

Causal Inference Opening Workshop - Latent Variable Models, Causal Inference,...
Causal Inference Opening Workshop - Latent Variable Models, Causal Inference,...Causal Inference Opening Workshop - Latent Variable Models, Causal Inference,...
Causal Inference Opening Workshop - Latent Variable Models, Causal Inference,...
 
2019 Fall Series: Special Guest Lecture - 0-1 Phase Transitions in High Dimen...
2019 Fall Series: Special Guest Lecture - 0-1 Phase Transitions in High Dimen...2019 Fall Series: Special Guest Lecture - 0-1 Phase Transitions in High Dimen...
2019 Fall Series: Special Guest Lecture - 0-1 Phase Transitions in High Dimen...
 
Causal Inference Opening Workshop - Causal Discovery in Neuroimaging Data - F...
Causal Inference Opening Workshop - Causal Discovery in Neuroimaging Data - F...Causal Inference Opening Workshop - Causal Discovery in Neuroimaging Data - F...
Causal Inference Opening Workshop - Causal Discovery in Neuroimaging Data - F...
 
Causal Inference Opening Workshop - Smooth Extensions to BART for Heterogeneo...
Causal Inference Opening Workshop - Smooth Extensions to BART for Heterogeneo...Causal Inference Opening Workshop - Smooth Extensions to BART for Heterogeneo...
Causal Inference Opening Workshop - Smooth Extensions to BART for Heterogeneo...
 
Causal Inference Opening Workshop - A Bracketing Relationship between Differe...
Causal Inference Opening Workshop - A Bracketing Relationship between Differe...Causal Inference Opening Workshop - A Bracketing Relationship between Differe...
Causal Inference Opening Workshop - A Bracketing Relationship between Differe...
 
Causal Inference Opening Workshop - Testing Weak Nulls in Matched Observation...
Causal Inference Opening Workshop - Testing Weak Nulls in Matched Observation...Causal Inference Opening Workshop - Testing Weak Nulls in Matched Observation...
Causal Inference Opening Workshop - Testing Weak Nulls in Matched Observation...
 
Causal Inference Opening Workshop - Difference-in-differences: more than meet...
Causal Inference Opening Workshop - Difference-in-differences: more than meet...Causal Inference Opening Workshop - Difference-in-differences: more than meet...
Causal Inference Opening Workshop - Difference-in-differences: more than meet...
 
Causal Inference Opening Workshop - New Statistical Learning Methods for Esti...
Causal Inference Opening Workshop - New Statistical Learning Methods for Esti...Causal Inference Opening Workshop - New Statistical Learning Methods for Esti...
Causal Inference Opening Workshop - New Statistical Learning Methods for Esti...
 
Causal Inference Opening Workshop - Bipartite Causal Inference with Interfere...
Causal Inference Opening Workshop - Bipartite Causal Inference with Interfere...Causal Inference Opening Workshop - Bipartite Causal Inference with Interfere...
Causal Inference Opening Workshop - Bipartite Causal Inference with Interfere...
 
Causal Inference Opening Workshop - Bridging the Gap Between Causal Literatur...
Causal Inference Opening Workshop - Bridging the Gap Between Causal Literatur...Causal Inference Opening Workshop - Bridging the Gap Between Causal Literatur...
Causal Inference Opening Workshop - Bridging the Gap Between Causal Literatur...
 
Causal Inference Opening Workshop - Some Applications of Reinforcement Learni...
Causal Inference Opening Workshop - Some Applications of Reinforcement Learni...Causal Inference Opening Workshop - Some Applications of Reinforcement Learni...
Causal Inference Opening Workshop - Some Applications of Reinforcement Learni...
 
Causal Inference Opening Workshop - Bracketing Bounds for Differences-in-Diff...
Causal Inference Opening Workshop - Bracketing Bounds for Differences-in-Diff...Causal Inference Opening Workshop - Bracketing Bounds for Differences-in-Diff...
Causal Inference Opening Workshop - Bracketing Bounds for Differences-in-Diff...
 
Causal Inference Opening Workshop - Assisting the Impact of State Polcies: Br...
Causal Inference Opening Workshop - Assisting the Impact of State Polcies: Br...Causal Inference Opening Workshop - Assisting the Impact of State Polcies: Br...
Causal Inference Opening Workshop - Assisting the Impact of State Polcies: Br...
 
Causal Inference Opening Workshop - Experimenting in Equilibrium - Stefan Wag...
Causal Inference Opening Workshop - Experimenting in Equilibrium - Stefan Wag...Causal Inference Opening Workshop - Experimenting in Equilibrium - Stefan Wag...
Causal Inference Opening Workshop - Experimenting in Equilibrium - Stefan Wag...
 
Causal Inference Opening Workshop - Targeted Learning for Causal Inference Ba...
Causal Inference Opening Workshop - Targeted Learning for Causal Inference Ba...Causal Inference Opening Workshop - Targeted Learning for Causal Inference Ba...
Causal Inference Opening Workshop - Targeted Learning for Causal Inference Ba...
 
Causal Inference Opening Workshop - Bayesian Nonparametric Models for Treatme...
Causal Inference Opening Workshop - Bayesian Nonparametric Models for Treatme...Causal Inference Opening Workshop - Bayesian Nonparametric Models for Treatme...
Causal Inference Opening Workshop - Bayesian Nonparametric Models for Treatme...
 
2019 Fall Series: Special Guest Lecture - Adversarial Risk Analysis of the Ge...
2019 Fall Series: Special Guest Lecture - Adversarial Risk Analysis of the Ge...2019 Fall Series: Special Guest Lecture - Adversarial Risk Analysis of the Ge...
2019 Fall Series: Special Guest Lecture - Adversarial Risk Analysis of the Ge...
 
2019 Fall Series: Professional Development, Writing Academic Papers…What Work...
2019 Fall Series: Professional Development, Writing Academic Papers…What Work...2019 Fall Series: Professional Development, Writing Academic Papers…What Work...
2019 Fall Series: Professional Development, Writing Academic Papers…What Work...
 
2019 GDRR: Blockchain Data Analytics - Machine Learning in/for Blockchain: Fu...
2019 GDRR: Blockchain Data Analytics - Machine Learning in/for Blockchain: Fu...2019 GDRR: Blockchain Data Analytics - Machine Learning in/for Blockchain: Fu...
2019 GDRR: Blockchain Data Analytics - Machine Learning in/for Blockchain: Fu...
 
2019 GDRR: Blockchain Data Analytics - QuTrack: Model Life Cycle Management f...
2019 GDRR: Blockchain Data Analytics - QuTrack: Model Life Cycle Management f...2019 GDRR: Blockchain Data Analytics - QuTrack: Model Life Cycle Management f...
2019 GDRR: Blockchain Data Analytics - QuTrack: Model Life Cycle Management f...
 

Recently uploaded

Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...Marc Dusseiller Dusjagr
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceSamikshaHamane
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdfssuser54595a
 
Meghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentMeghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentInMediaRes1
 
History Class XII Ch. 3 Kinship, Caste and Class (1).pptx
History Class XII Ch. 3 Kinship, Caste and Class (1).pptxHistory Class XII Ch. 3 Kinship, Caste and Class (1).pptx
History Class XII Ch. 3 Kinship, Caste and Class (1).pptxsocialsciencegdgrohi
 
Pharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfPharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfMahmoud M. Sallam
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxNirmalaLoungPoorunde1
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Types of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxTypes of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxEyham Joco
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17Celine George
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxOH TEIK BIN
 
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,Virag Sontakke
 
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxEPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxRaymartEstabillo3
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptxVS Mahajan Coaching Centre
 
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfFraming an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfUjwalaBharambe
 

Recently uploaded (20)

Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
“Oh GOSH! Reflecting on Hackteria's Collaborative Practices in a Global Do-It...
 
Roles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in PharmacovigilanceRoles & Responsibilities in Pharmacovigilance
Roles & Responsibilities in Pharmacovigilance
 
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
18-04-UA_REPORT_MEDIALITERAСY_INDEX-DM_23-1-final-eng.pdf
 
Meghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media ComponentMeghan Sutherland In Media Res Media Component
Meghan Sutherland In Media Res Media Component
 
History Class XII Ch. 3 Kinship, Caste and Class (1).pptx
History Class XII Ch. 3 Kinship, Caste and Class (1).pptxHistory Class XII Ch. 3 Kinship, Caste and Class (1).pptx
History Class XII Ch. 3 Kinship, Caste and Class (1).pptx
 
Pharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdfPharmacognosy Flower 3. Compositae 2023.pdf
Pharmacognosy Flower 3. Compositae 2023.pdf
 
Employee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptxEmployee wellbeing at the workplace.pptx
Employee wellbeing at the workplace.pptx
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)ESSENTIAL of (CS/IT/IS) class 06 (database)
ESSENTIAL of (CS/IT/IS) class 06 (database)
 
Types of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptxTypes of Journalistic Writing Grade 8.pptx
Types of Journalistic Writing Grade 8.pptx
 
How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17How to Configure Email Server in Odoo 17
How to Configure Email Server in Odoo 17
 
Solving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptxSolving Puzzles Benefits Everyone (English).pptx
Solving Puzzles Benefits Everyone (English).pptx
 
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdfTataKelola dan KamSiber Kecerdasan Buatan v022.pdf
TataKelola dan KamSiber Kecerdasan Buatan v022.pdf
 
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,भारत-रोम व्यापार.pptx, Indo-Roman Trade,
भारत-रोम व्यापार.pptx, Indo-Roman Trade,
 
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptxEPANDING THE CONTENT OF AN OUTLINE using notes.pptx
EPANDING THE CONTENT OF AN OUTLINE using notes.pptx
 
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions  for the students and aspirants of Chemistry12th.pptxOrganic Name Reactions  for the students and aspirants of Chemistry12th.pptx
Organic Name Reactions for the students and aspirants of Chemistry12th.pptx
 
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdfFraming an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
Framing an Appropriate Research Question 6b9b26d93da94caf993c038d9efcdedb.pdf
 
OS-operating systems- ch04 (Threads) ...
OS-operating systems- ch04 (Threads) ...OS-operating systems- ch04 (Threads) ...
OS-operating systems- ch04 (Threads) ...
 

QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm without Cocoercivity - Saverio Salzo, Mar 22, 2018

  • 1. THE FORWARD-BACKWARD SPLITTING ALGORITHM WITHOUT COCOERCIVITY? Saverio Salzo Istituto Italiano di Tecnologia Genova, Italy Workshop on Operator Splitting Methods in Data Analysis Samsi, Durham, NC, March, 21-23, 2018
  • 2. is a real Hilbert space with scalar product is maximal monotone is -cocoercive, that is ZEROS OF SUM OF MONOTONE OPERATORS The problem H h· , ·i A: H ! 2H B : H ! H find ¯x 2 H s.t. 0 2 A(¯x) + B(¯x) kB(x) B(y)k2  hx y, B(x) B(y)i
  • 3. is a real Hilbert space with scalar product is maximal monotone if is
 proper, convex, and lower semicontinuous. is -cocoercive iff it is -Lipschitz continuous. MINIMIZATION OF SUM OF FUNCTIONS The problem h· , ·i find ¯x 2 H s.t. 0 2 @f(¯x) + rg(¯x) @f : H ! 2H f : H ! ] 1, +1] rg: H ! H (1/ ) H
  • 4. is a real Hilbert space with scalar product is maximal monotone if is
 nonempty, closed, and convex. is -cocoercive. VARIATIONAL INEQUALITIES The problem find ¯x 2 C s.t. 8 x 2 C h¯x x, B¯xi  0 A = @iC = NC C ⇢ H B : H ! H h· , ·iH
  • 5. THE FORWARD-BACKWARD SPLITTING (Mercier ’79) The algorithm if and , then
 xk+1 = J kA(xk kB(xk)) Convergence: if k < 2 xk * ¯x 2 zer(A + B) A = @f B = rg (f + g)(xk) inf(f + g) = o(1/k) Cocoercivity of is a fundamental assumption!B
  • 6. minimize x2Rd + DKL(b, Ax) + ⌧kxk1 minimize x2Rd 1 p kAx bkp p + ⌧kxk1 (p > 1) minimize w2Rd nX i=1 L(yi, hw, xii) + ⌧ p kwkp p (1 < p < 2) When cocoercivity is an issue
  • 7. minimize x2Rd 1 p kAx bkp p + ⌧kxk1 (p > 1) minimize ↵2Rn 1 q kX⇤ ↵kq q + 1 ⌧ nX i=1 L⇤ (yi, ⌧↵i) (q > 2) When cocoercivity is an issue minimize x2Rd + DKL(b, Ax) + ⌧kxk1
  • 8. TSENG’S SPLITTING (Tseng ’00) is maximal monotone is uniformly continuous on bounded sets is chosen by the backtracking procedure: let B : H ! H k kB(yk) B(xk)k  k kyk xkk 2 ]0, 1[ The algorithm converges if A: H ! 2H yk = J kA(xk kB(xk)) xk+1 = yk kB(yk) + kB(xk) Strategies without cocoercivity
  • 9. , is proper, convex, and lsc is uniformly continuous on bounded sets. is determined by backtracking line search procedures (a priori choices are not possible anymore). THE FORWARD-BACKWARD SPLITTING 
 FOR MINIMIZATION PROBLEMS xk+1 = J kA(xk kB(xk)) B = rg A = @f f : H ! ] 1, +1] k The algorithm converges if S. Salzo, The variable metric forward-backward splitting algorithm under mild differentiability assumptions. SIOPT 2017. Strategies without cocoercivity
  • 10. BACKTRACKING LINE SEARCHES L1) L2) L3) We considered three possible inequalities: let krg(xk+1) rg(xk)k  k kxk+1 xkk g(xk+1) g(xk) hxk+1 xk, rg(xk)i  k kxk+1 xkk2 (f + g)(xk+1) (f + g)(xk)  (1 ) f(xk+1) f(xk) + hxk+1 xk, rg(xk)i 2 ]0, 1[ L1) L2) L3) L1) is not quite appropriate for FB algorithm since it leads to halve the step-sizes w.r.t. L2) and L3) =) =) Strategies without cocoercivity
  • 11. FBA FBFA They work under exactly the same assumptions! MINIMIZATION PROBLEMS Strategies without cocoercivity
  • 12. THE PROBLEM: DEVISE AN APPROPRIATE BACKTRACKING LINESEARCH THAT REPLACES THE COCOERCIVITY What about the FB algorithm for 
 monotone operators? Removing cocoercivity
  • 13. Where does cocoercivity enter? kxk+1 ¯xk2  kxk ¯xk2 kxk+1 xkk2 2 khxk ¯x, B(xk) B(¯x)i 2 khxk+1 xk, B(xk) B(¯x)i = kxk ¯xk2 k(2 k)kB(xk) B(¯x)k2 k(xk+1 xk) k(B(xk) B(¯x))k2 FB ALGORITHM FOR MONOTONE OPERATORS
  • 14. Where does cocoercivity enter? FB ALGORITHM FOR MINIMIZATION PROBLEMS kxk+1 xk2  kxk xk2 kxk+1 xkk2 + 2 k (f + g)(x) (f + g)(xk) 2 k g(xk+1) g(xk) + hxk+1 xk, rg(xk)i  kxk xk2 + (2 1)kxk+1 xkk2 + 2 k (f + g)(x) (f + g)(xk) + 2 k (f + g)(xk) (f + g)(xk+1)
  • 15. Possible strategies only value of B?
 
 
 
 would not work! the values of function (to be determined), that hopefully should decrease along the iterations? k kB(xk+1) B(xk)k2  hB(xk+1) B(xk), xk+1 xki The inequality should involve:
  • 16. , Possible strategies PRIMAL DUAL ALGORITHMS min x2H g(x) + h(Lx) ✓ 0 0 ◆ 2 A ✓ ¯x ¯v ◆ + B ✓ ¯x ¯v ◆ A ✓ x v ◆ = ✓ L⇤ v @h⇤ (v) Lx ◆ B ✓ x v ◆ = ✓ rg(x) 0 ◆ is convex and continuously differentiable.g: H ! R (Combettes-Pesquet ’12, Condat ’13, Vu ’13) Should backtracking involve the duality gap function?