SlideShare a Scribd company logo
1 of 35
Download to read offline
Quantum Machine Learning
and QEM for Gaussian mixture models
Alessandro Luongo
Machine Learning Data Science Meetup
July 1, 2020
Iordanis Kerenidis: 1,3,4
Anupam Prakash: 4
AL: 1,2
In short:
We propose a quantum algorithm for
Expectation-Maximization
that fits a
Gaussian mixture model
(using quantum linear algebra, QRAM, distance estimation, etc..)
for a matrix V ∈ Rn×d in time complexity:
O
d2k4.5η3.5κ2(V )κ2(Σ)µ(V )
δ3
log n .
In short:
We propose a quantum algorithm for
Expectation-Maximization
that fits a
Gaussian mixture model
(using quantum linear algebra, QRAM, distance estimation, etc..)
for a matrix V ∈ Rn×d in time complexity:
O
d2k4.5η3.5κ2(V )κ2(Σ)µ(V )
δ3
log n .
Notation & quantum information 101 - part 1
Qubit: any unit vector in C2.
Basis for this space: |0 = [1, 0]T , |1 = [0, 1]T
|ψ = α |0 + β |1 s.t. |α2
| + |β2
| = 1
Tensor product between vectors:
[a, b] ⊗ [c, d] = [ac, ad, bc, bd]
Quantum state are vectors. Let x ∈ Rd , then:
|x =
1
x 2
x =
1
x 2
2n
i=1
xi |i
Note: |x has log d qubits!
Measuring quantum state |x :
p(|i ) = x2
i / x 2
Notation & quantum information 101 - part 2
A Quantum program is a unitary matrix U
|y = U |x
Quantum circuit is composed of elementary quantum gates:
NOT =
0 1
1 0
H =
1
√
2
1 1
1 −1
Runtime of quantum algorithm = depth of circuit.
Quantum Machine Learning Toolkit
1. Grover-like algorithms
2. Quantum access to classical data
3. Quantum linear algebra
4. Distance estimation
5. Tomography
(others: amplification techniques, Hamiltonian simulations, etc..)
Grover’s Algorithm
Problem: Given a function f : {0, 1}n
→ {0, 1}, find the only x
such that f (x) = 1.
Classically: It takes O(2n).
Grover’s Algorithm
Problem: Given a function f : {0, 1}n
→ {0, 1}, find the only x
such that f (x) = 1.
Classically: It takes O(2n).
Theorem [Grover algorithm (informal)]
There exists an algorithm that finds x such that f (x) = 1 in time
O(
√
2n)
Quantum access to classical matrices
Let V ∈ Rn×d ,
with vi row of V ,
1
V F i
vi |i |vi (1)
Quantum access to classical matrices
Let V ∈ Rn×d ,
with vi row of V ,
1
V F i
vi |i |vi (1)
Facts:
Preparation (preprocessing) time: O(nd log nd)
Size: O(nd log nd)
Execution time: O(log nd)
Can be implemented with a generalization of the QRAM,
(PhD thesis of A. Prakash)
Quantum linear algebra
“Solve” linear systems Ax = b
Breakthrough! - HHL algorithm in 2009
Assuming quantum access to matrix A ∈ Rn×d
Encode b ∈ Rd as |b
We can prepare |A−1b or |Ab , in O µ(A)κ(A)
Norm A−1b is estimated with rel. error with additional
O(1/ ) time.
Distance estimation
What: With quantum access to matrices V , C:
|i |j |0 → |i |j |d(vi , cj )
distance between row i of V and j of C.
Error: relative
Time: O η
where η = maxi,j ( vi
2
+ cj
2
)
Tomography
Retrieving data from quantum computers
For a quantum state |x ∈ Rd we get classical estimate x
|x − x 2 ≤ δ by generating |x O d/δ2 times.
|x − x ∞ ≤ δ by generating |x O log(d)/δ2 times.
Also, sampling, amplitude estimation..
Credit: Wikipedia user: Chire (CC BY-SA 3.0)
Gaussian mixture models (GMM)
Assumption on data (vi , yi ). Is generated by:
1. Sampling a label yi ∈ [k] according to Mult(θ),
2. Sampling a vector vi according to N(µyi , Σyi ).
Mult(θ): multinomial distribution (a dice) for θ ∈ Rk
N(µyi , Σyi ): multivariate Gaussian distribution
GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
Gaussian mixture models (GMM)
Assumption on data (vi , yi ). Is generated by:
1. Sampling a label yi ∈ [k] according to Mult(θ),
2. Sampling a vector vi according to N(µyi , Σyi ).
Mult(θ): multinomial distribution (a dice) for θ ∈ Rk
N(µyi , Σyi ): multivariate Gaussian distribution
GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
Robust GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
Gaussian mixture models (GMM)
Assumption on data (vi , yi ). Is generated by:
1. Sampling a label yi ∈ [k] according to Mult(θ),
2. Sampling a vector vi according to N(µyi , Σyi ).
Mult(θ): multinomial distribution (a dice) for θ ∈ Rk
N(µyi , Σyi ): multivariate Gaussian distribution
GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
Robust GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
θ − θ ≤ δθ, µj − µj ≤ δµ, Σj − Σj ≤ δµ
√
η
Classical EM for GMM: O(tndω
k)
1: repeat
2: Expectation
rt
ij =
θt
j N(vi ; µt
j , Σt
j )
k
l=1 θt
l N(vi ; µt
l , Σt
l )
∀i ∈ [n], j ∈ [k]
3: Maximization
Update the parameters of the model as:
θt+1
j ←
1
n
n
i=1
rt
ij
µt+1
j ←
n
i=1 rt
ij vi
n
i=1 rt
ij
Σt+1
j ←
n
i=1 rt
ij (vi − µt+1
j )(vi − µt+1
j )T
n
i=1 rt
ij
4: t=t+1
5: until | (γt−1; V ) − (γt; V )| < τ
Quantum Expectation
We want estimate:
rij = p(vi |j)
We build
U |i |j → |i |j |rij
and
U |j |0 → |j
1
Rj
n
i
rij |i
Error: additive
Time:
˜O(
k1.5ηκ(Σ)
δ
)
Quantum Maximization θt+1
We want:
θt+1
j ←
1
n
n
i=1
rt
ij
Trick: Use Expectation Step and amplitude amplification to build:
|
√
R :=
k
j=1
θj
t+1
| Rj |j . (2)
Error:
θ
t
− θt
< δθ
Runtime:
Tθ = O k3.5
η1.5 κ2(Σ)µ(Σ)
δ2
θ
log n
VoxForge dataset: Speaker recognition
Σ 2 |logdet(Σ)| κ∗
(Σ) µ(Σ) µ(V ) κ(V )
MAP
avg 0.244 58.56 4.21 3.82 2.14 23.82
max 2.45 70.08 50 4.35 2.79 40.38
ML
avg 1.31 14.56 15.57 2.54 2.14 23.82
max 3.44 92,3 50 3.67 2.79 40.38
η = 13
Classical accuracy: 98.8%
Quantum accuracy: 98.2%
Comparable number of iterations
Variational circuits - another paradigm for QML
Credit: Dawid Kopczyk
De-quantizations
Sampling-based sublinear low-rank matrix arithmetic
framework for dequantizing quantum machine learning
-Nai-Hui Chia, Andr´as Gily´en, Tongyang Li, Han-Hsuan Lin,
Ewin Tang, Chunhao Wang [1910.06151]
Quantum-Inspired Classical Algorithms for Singular Value
Transformation - Dhawal Jethwani, Fran¸cois Le Gall, Sanjay
K. Singh [1910.05699]
... but also...
Arrazola, Juan Miguel, et al. ”Quantum-inspired algorithms in
practice.” arXiv preprint [1905.10415] .
Dequantized recommandation system’ runtimes:
O
A 24
F
12σ24
Conclusions
We made well-clusterability assumptions,
... but we have runtime guarantees on non well-clusterable
datasets!
We have also quantum initialization strategies!
QEM works for all base distributions in exponential family!
Faster quantum algorithms for the log-determinant soon! :)

More Related Content

What's hot

Fast Identification of Heavy Hitters by Cached and Packed Group Testing
Fast Identification of Heavy Hitters by Cached and Packed Group TestingFast Identification of Heavy Hitters by Cached and Packed Group Testing
Fast Identification of Heavy Hitters by Cached and Packed Group TestingRakuten Group, Inc.
 
Low-rank tensor approximation (Introduction)
Low-rank tensor approximation (Introduction)Low-rank tensor approximation (Introduction)
Low-rank tensor approximation (Introduction)Alexander Litvinenko
 
Coordinate sampler: A non-reversible Gibbs-like sampler
Coordinate sampler: A non-reversible Gibbs-like samplerCoordinate sampler: A non-reversible Gibbs-like sampler
Coordinate sampler: A non-reversible Gibbs-like samplerChristian Robert
 
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra Sahil Kumar
 
A Commutative Alternative to Fractional Calculus on k-Differentiable Functions
A Commutative Alternative to Fractional Calculus on k-Differentiable FunctionsA Commutative Alternative to Fractional Calculus on k-Differentiable Functions
A Commutative Alternative to Fractional Calculus on k-Differentiable FunctionsMatt Parker
 
Path Contraction Faster than 2^n
Path Contraction Faster than 2^nPath Contraction Faster than 2^n
Path Contraction Faster than 2^nAkankshaAgrawal55
 
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML
 
Fast Wavelet Tree Construction in Practice
Fast Wavelet Tree Construction in PracticeFast Wavelet Tree Construction in Practice
Fast Wavelet Tree Construction in PracticeRakuten Group, Inc.
 
Nearly optimal average case complexity of counting bicliques under seth
Nearly optimal average case complexity of counting bicliques under sethNearly optimal average case complexity of counting bicliques under seth
Nearly optimal average case complexity of counting bicliques under sethNobutaka Shimizu
 
Context-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationContext-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationDmitrii Ignatov
 
Fine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its VariantsFine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its VariantsAkankshaAgrawal55
 
SIAM - Minisymposium on Guaranteed numerical algorithms
SIAM - Minisymposium on Guaranteed numerical algorithmsSIAM - Minisymposium on Guaranteed numerical algorithms
SIAM - Minisymposium on Guaranteed numerical algorithmsJagadeeswaran Rathinavel
 
Brief summary of signals
Brief summary of signalsBrief summary of signals
Brief summary of signalsaroosa khan
 
Hierarchical matrices for approximating large covariance matries and computin...
Hierarchical matrices for approximating large covariance matries and computin...Hierarchical matrices for approximating large covariance matries and computin...
Hierarchical matrices for approximating large covariance matries and computin...Alexander Litvinenko
 
HMPC for Upper Stage Attitude Control
HMPC for Upper Stage Attitude ControlHMPC for Upper Stage Attitude Control
HMPC for Upper Stage Attitude ControlPantelis Sopasakis
 

What's hot (20)

Fast Identification of Heavy Hitters by Cached and Packed Group Testing
Fast Identification of Heavy Hitters by Cached and Packed Group TestingFast Identification of Heavy Hitters by Cached and Packed Group Testing
Fast Identification of Heavy Hitters by Cached and Packed Group Testing
 
Low-rank tensor approximation (Introduction)
Low-rank tensor approximation (Introduction)Low-rank tensor approximation (Introduction)
Low-rank tensor approximation (Introduction)
 
Coordinate sampler: A non-reversible Gibbs-like sampler
Coordinate sampler: A non-reversible Gibbs-like samplerCoordinate sampler: A non-reversible Gibbs-like sampler
Coordinate sampler: A non-reversible Gibbs-like sampler
 
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra
ADA - Minimum Spanning Tree Prim Kruskal and Dijkstra
 
A Commutative Alternative to Fractional Calculus on k-Differentiable Functions
A Commutative Alternative to Fractional Calculus on k-Differentiable FunctionsA Commutative Alternative to Fractional Calculus on k-Differentiable Functions
A Commutative Alternative to Fractional Calculus on k-Differentiable Functions
 
Path Contraction Faster than 2^n
Path Contraction Faster than 2^nPath Contraction Faster than 2^n
Path Contraction Faster than 2^n
 
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information SystemsRuleML2015: Learning Characteristic Rules in Geographic Information Systems
RuleML2015: Learning Characteristic Rules in Geographic Information Systems
 
Chris Sherlock's slides
Chris Sherlock's slidesChris Sherlock's slides
Chris Sherlock's slides
 
Fast Wavelet Tree Construction in Practice
Fast Wavelet Tree Construction in PracticeFast Wavelet Tree Construction in Practice
Fast Wavelet Tree Construction in Practice
 
Nearly optimal average case complexity of counting bicliques under seth
Nearly optimal average case complexity of counting bicliques under sethNearly optimal average case complexity of counting bicliques under seth
Nearly optimal average case complexity of counting bicliques under seth
 
Context-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix FactorisationContext-Aware Recommender System Based on Boolean Matrix Factorisation
Context-Aware Recommender System Based on Boolean Matrix Factorisation
 
Fine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its VariantsFine Grained Complexity of Rainbow Coloring and its Variants
Fine Grained Complexity of Rainbow Coloring and its Variants
 
Ponchon Savarait
Ponchon SavaraitPonchon Savarait
Ponchon Savarait
 
SIAM - Minisymposium on Guaranteed numerical algorithms
SIAM - Minisymposium on Guaranteed numerical algorithmsSIAM - Minisymposium on Guaranteed numerical algorithms
SIAM - Minisymposium on Guaranteed numerical algorithms
 
Richard Everitt's slides
Richard Everitt's slidesRichard Everitt's slides
Richard Everitt's slides
 
Brief summary of signals
Brief summary of signalsBrief summary of signals
Brief summary of signals
 
Hierarchical matrices for approximating large covariance matries and computin...
Hierarchical matrices for approximating large covariance matries and computin...Hierarchical matrices for approximating large covariance matries and computin...
Hierarchical matrices for approximating large covariance matries and computin...
 
Prim algorithm
Prim algorithmPrim algorithm
Prim algorithm
 
HMPC for Upper Stage Attitude Control
HMPC for Upper Stage Attitude ControlHMPC for Upper Stage Attitude Control
HMPC for Upper Stage Attitude Control
 
QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm withou...
QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm withou...QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm withou...
QMC: Operator Splitting Workshop, Forward-Backward Splitting Algorithm withou...
 

Similar to Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)

SPDE presentation 2012
SPDE presentation 2012SPDE presentation 2012
SPDE presentation 2012Zheng Mengdi
 
Comparing estimation algorithms for block clustering models
Comparing estimation algorithms for block clustering modelsComparing estimation algorithms for block clustering models
Comparing estimation algorithms for block clustering modelsBigMC
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Valentin De Bortoli
 
parameterized complexity for graph Motif
parameterized complexity for graph Motifparameterized complexity for graph Motif
parameterized complexity for graph MotifAMR koura
 
Bayesian inference on mixtures
Bayesian inference on mixturesBayesian inference on mixtures
Bayesian inference on mixturesChristian Robert
 
Response Surface in Tensor Train format for Uncertainty Quantification
Response Surface in Tensor Train format for Uncertainty QuantificationResponse Surface in Tensor Train format for Uncertainty Quantification
Response Surface in Tensor Train format for Uncertainty QuantificationAlexander Litvinenko
 
Q-Metrics in Theory and Practice
Q-Metrics in Theory and PracticeQ-Metrics in Theory and Practice
Q-Metrics in Theory and PracticeMagdi Mohamed
 
Q-Metrics in Theory And Practice
Q-Metrics in Theory And PracticeQ-Metrics in Theory And Practice
Q-Metrics in Theory And Practiceguest3550292
 
A Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeA Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeVjekoslavKovac1
 
Tensor Train data format for uncertainty quantification
Tensor Train data format for uncertainty quantificationTensor Train data format for uncertainty quantification
Tensor Train data format for uncertainty quantificationAlexander Litvinenko
 
Processing Reachability Queries with Realistic Constraints on Massive Network...
Processing Reachability Queries with Realistic Constraints on Massive Network...Processing Reachability Queries with Realistic Constraints on Massive Network...
Processing Reachability Queries with Realistic Constraints on Massive Network...BigMine
 
Distributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUsDistributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUsPantelis Sopasakis
 
Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Fabian Pedregosa
 
Testing for mixtures by seeking components
Testing for mixtures by seeking componentsTesting for mixtures by seeking components
Testing for mixtures by seeking componentsChristian Robert
 
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHS
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHSDISTANCE TWO LABELING FOR MULTI-STOREY GRAPHS
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHSgraphhoc
 
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...Michael Lie
 

Similar to Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo) (20)

SPDE presentation 2012
SPDE presentation 2012SPDE presentation 2012
SPDE presentation 2012
 
Comparing estimation algorithms for block clustering models
Comparing estimation algorithms for block clustering modelsComparing estimation algorithms for block clustering models
Comparing estimation algorithms for block clustering models
 
Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...Maximum likelihood estimation of regularisation parameters in inverse problem...
Maximum likelihood estimation of regularisation parameters in inverse problem...
 
parameterized complexity for graph Motif
parameterized complexity for graph Motifparameterized complexity for graph Motif
parameterized complexity for graph Motif
 
Bayesian inference on mixtures
Bayesian inference on mixturesBayesian inference on mixtures
Bayesian inference on mixtures
 
Response Surface in Tensor Train format for Uncertainty Quantification
Response Surface in Tensor Train format for Uncertainty QuantificationResponse Surface in Tensor Train format for Uncertainty Quantification
Response Surface in Tensor Train format for Uncertainty Quantification
 
Q-Metrics in Theory and Practice
Q-Metrics in Theory and PracticeQ-Metrics in Theory and Practice
Q-Metrics in Theory and Practice
 
Q-Metrics in Theory And Practice
Q-Metrics in Theory And PracticeQ-Metrics in Theory And Practice
Q-Metrics in Theory And Practice
 
Codes and Isogenies
Codes and IsogeniesCodes and Isogenies
Codes and Isogenies
 
The Gaussian Hardy-Littlewood Maximal Function
The Gaussian Hardy-Littlewood Maximal FunctionThe Gaussian Hardy-Littlewood Maximal Function
The Gaussian Hardy-Littlewood Maximal Function
 
A Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cubeA Szemeredi-type theorem for subsets of the unit cube
A Szemeredi-type theorem for subsets of the unit cube
 
Tensor Train data format for uncertainty quantification
Tensor Train data format for uncertainty quantificationTensor Train data format for uncertainty quantification
Tensor Train data format for uncertainty quantification
 
Processing Reachability Queries with Realistic Constraints on Massive Network...
Processing Reachability Queries with Realistic Constraints on Massive Network...Processing Reachability Queries with Realistic Constraints on Massive Network...
Processing Reachability Queries with Realistic Constraints on Massive Network...
 
Distributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUsDistributed solution of stochastic optimal control problem on GPUs
Distributed solution of stochastic optimal control problem on GPUs
 
Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3Random Matrix Theory and Machine Learning - Part 3
Random Matrix Theory and Machine Learning - Part 3
 
Testing for mixtures by seeking components
Testing for mixtures by seeking componentsTesting for mixtures by seeking components
Testing for mixtures by seeking components
 
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHS
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHSDISTANCE TWO LABELING FOR MULTI-STOREY GRAPHS
DISTANCE TWO LABELING FOR MULTI-STOREY GRAPHS
 
cheb_conf_aksenov.pdf
cheb_conf_aksenov.pdfcheb_conf_aksenov.pdf
cheb_conf_aksenov.pdf
 
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...
Time-Series Analysis on Multiperiodic Conditional Correlation by Sparse Covar...
 
Automatic bayesian cubature
Automatic bayesian cubatureAutomatic bayesian cubature
Automatic bayesian cubature
 

More from MeetupDataScienceRoma

Serve Davvero il Machine Learning nelle PMI? | Niccolò Annino
Serve Davvero il Machine Learning nelle PMI? | Niccolò AnninoServe Davvero il Machine Learning nelle PMI? | Niccolò Annino
Serve Davvero il Machine Learning nelle PMI? | Niccolò AnninoMeetupDataScienceRoma
 
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...MeetupDataScienceRoma
 
Claudio Gallicchio - Deep Reservoir Computing for Structured Data
Claudio Gallicchio - Deep Reservoir Computing for Structured DataClaudio Gallicchio - Deep Reservoir Computing for Structured Data
Claudio Gallicchio - Deep Reservoir Computing for Structured DataMeetupDataScienceRoma
 
Docker for Deep Learning (Andrea Panizza)
Docker for Deep Learning (Andrea Panizza)Docker for Deep Learning (Andrea Panizza)
Docker for Deep Learning (Andrea Panizza)MeetupDataScienceRoma
 
Machine Learning for Epidemiological Models (Enrico Meloni)
Machine Learning for Epidemiological Models (Enrico Meloni)Machine Learning for Epidemiological Models (Enrico Meloni)
Machine Learning for Epidemiological Models (Enrico Meloni)MeetupDataScienceRoma
 
Web Meetup #2: Modelli matematici per l'epidemiologia
Web Meetup #2: Modelli matematici per l'epidemiologiaWeb Meetup #2: Modelli matematici per l'epidemiologia
Web Meetup #2: Modelli matematici per l'epidemiologiaMeetupDataScienceRoma
 
Deep red - The environmental impact of deep learning (Paolo Caressa)
Deep red - The environmental impact of deep learning (Paolo Caressa)Deep red - The environmental impact of deep learning (Paolo Caressa)
Deep red - The environmental impact of deep learning (Paolo Caressa)MeetupDataScienceRoma
 
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...MeetupDataScienceRoma
 
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)Multimodal AI Approach to Provide Assistive Services (Francesco Puja)
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)MeetupDataScienceRoma
 
Introduzione - Meetup MLOps & Assistive AI
Introduzione - Meetup MLOps & Assistive AIIntroduzione - Meetup MLOps & Assistive AI
Introduzione - Meetup MLOps & Assistive AIMeetupDataScienceRoma
 
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)MeetupDataScienceRoma
 
Mario Incarnati - The power of data visualization
Mario Incarnati - The power of data visualizationMario Incarnati - The power of data visualization
Mario Incarnati - The power of data visualizationMeetupDataScienceRoma
 
OLIVAW: reaching superhuman strength at Othello
OLIVAW: reaching superhuman strength at OthelloOLIVAW: reaching superhuman strength at Othello
OLIVAW: reaching superhuman strength at OthelloMeetupDataScienceRoma
 
[Giovanni Galloro] How to use machine learning on Google Cloud Platform
[Giovanni Galloro] How to use machine learning on Google Cloud Platform[Giovanni Galloro] How to use machine learning on Google Cloud Platform
[Giovanni Galloro] How to use machine learning on Google Cloud PlatformMeetupDataScienceRoma
 
Bring your neural networks to the browser with TF.js - Simone Scardapane
Bring your neural networks to the browser with TF.js - Simone ScardapaneBring your neural networks to the browser with TF.js - Simone Scardapane
Bring your neural networks to the browser with TF.js - Simone ScardapaneMeetupDataScienceRoma
 
Meetup Gennaio 2019 - Slide introduttiva
Meetup Gennaio 2019 - Slide introduttivaMeetup Gennaio 2019 - Slide introduttiva
Meetup Gennaio 2019 - Slide introduttivaMeetupDataScienceRoma
 
Bruno Coletta - Data-Driven Creativity in Marketing and Advertising
Bruno Coletta - Data-Driven Creativity in Marketing and AdvertisingBruno Coletta - Data-Driven Creativity in Marketing and Advertising
Bruno Coletta - Data-Driven Creativity in Marketing and AdvertisingMeetupDataScienceRoma
 

More from MeetupDataScienceRoma (20)

Serve Davvero il Machine Learning nelle PMI? | Niccolò Annino
Serve Davvero il Machine Learning nelle PMI? | Niccolò AnninoServe Davvero il Machine Learning nelle PMI? | Niccolò Annino
Serve Davvero il Machine Learning nelle PMI? | Niccolò Annino
 
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...
Meta-learning through the lenses of Statistical Learning Theory (Carlo Cilibe...
 
Claudio Gallicchio - Deep Reservoir Computing for Structured Data
Claudio Gallicchio - Deep Reservoir Computing for Structured DataClaudio Gallicchio - Deep Reservoir Computing for Structured Data
Claudio Gallicchio - Deep Reservoir Computing for Structured Data
 
Docker for Deep Learning (Andrea Panizza)
Docker for Deep Learning (Andrea Panizza)Docker for Deep Learning (Andrea Panizza)
Docker for Deep Learning (Andrea Panizza)
 
Machine Learning for Epidemiological Models (Enrico Meloni)
Machine Learning for Epidemiological Models (Enrico Meloni)Machine Learning for Epidemiological Models (Enrico Meloni)
Machine Learning for Epidemiological Models (Enrico Meloni)
 
Web Meetup #2: Modelli matematici per l'epidemiologia
Web Meetup #2: Modelli matematici per l'epidemiologiaWeb Meetup #2: Modelli matematici per l'epidemiologia
Web Meetup #2: Modelli matematici per l'epidemiologia
 
Deep red - The environmental impact of deep learning (Paolo Caressa)
Deep red - The environmental impact of deep learning (Paolo Caressa)Deep red - The environmental impact of deep learning (Paolo Caressa)
Deep red - The environmental impact of deep learning (Paolo Caressa)
 
[Sponsored] C3.ai description
[Sponsored] C3.ai description[Sponsored] C3.ai description
[Sponsored] C3.ai description
 
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...
Paolo Galeone - Dissecting tf.function to discover auto graph strengths and s...
 
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)Multimodal AI Approach to Provide Assistive Services (Francesco Puja)
Multimodal AI Approach to Provide Assistive Services (Francesco Puja)
 
Introduzione - Meetup MLOps & Assistive AI
Introduzione - Meetup MLOps & Assistive AIIntroduzione - Meetup MLOps & Assistive AI
Introduzione - Meetup MLOps & Assistive AI
 
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)
Zero, One, Many - Machine Learning in Produzione (Luca Palmieri)
 
Mario Incarnati - The power of data visualization
Mario Incarnati - The power of data visualizationMario Incarnati - The power of data visualization
Mario Incarnati - The power of data visualization
 
Machine Learning in the AWS Cloud
Machine Learning in the AWS CloudMachine Learning in the AWS Cloud
Machine Learning in the AWS Cloud
 
OLIVAW: reaching superhuman strength at Othello
OLIVAW: reaching superhuman strength at OthelloOLIVAW: reaching superhuman strength at Othello
OLIVAW: reaching superhuman strength at Othello
 
[Giovanni Galloro] How to use machine learning on Google Cloud Platform
[Giovanni Galloro] How to use machine learning on Google Cloud Platform[Giovanni Galloro] How to use machine learning on Google Cloud Platform
[Giovanni Galloro] How to use machine learning on Google Cloud Platform
 
Bring your neural networks to the browser with TF.js - Simone Scardapane
Bring your neural networks to the browser with TF.js - Simone ScardapaneBring your neural networks to the browser with TF.js - Simone Scardapane
Bring your neural networks to the browser with TF.js - Simone Scardapane
 
Meetup Gennaio 2019 - Slide introduttiva
Meetup Gennaio 2019 - Slide introduttivaMeetup Gennaio 2019 - Slide introduttiva
Meetup Gennaio 2019 - Slide introduttiva
 
Elena Gagliardoni - Neural Chatbot
Elena Gagliardoni - Neural ChatbotElena Gagliardoni - Neural Chatbot
Elena Gagliardoni - Neural Chatbot
 
Bruno Coletta - Data-Driven Creativity in Marketing and Advertising
Bruno Coletta - Data-Driven Creativity in Marketing and AdvertisingBruno Coletta - Data-Driven Creativity in Marketing and Advertising
Bruno Coletta - Data-Driven Creativity in Marketing and Advertising
 

Recently uploaded

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsAndrey Dotsenko
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxnull - The Open Security Community
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 

Recently uploaded (20)

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptxMaking_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
Making_way_through_DLL_hollowing_inspite_of_CFG_by_Debjeet Banerjee.pptx
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort ServiceHot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
 

Quantum Machine Learning and QEM for Gaussian mixture models (Alessandro Luongo)

  • 1. Quantum Machine Learning and QEM for Gaussian mixture models Alessandro Luongo Machine Learning Data Science Meetup July 1, 2020 Iordanis Kerenidis: 1,3,4 Anupam Prakash: 4 AL: 1,2
  • 2.
  • 3. In short: We propose a quantum algorithm for Expectation-Maximization that fits a Gaussian mixture model (using quantum linear algebra, QRAM, distance estimation, etc..) for a matrix V ∈ Rn×d in time complexity: O d2k4.5η3.5κ2(V )κ2(Σ)µ(V ) δ3 log n .
  • 4. In short: We propose a quantum algorithm for Expectation-Maximization that fits a Gaussian mixture model (using quantum linear algebra, QRAM, distance estimation, etc..) for a matrix V ∈ Rn×d in time complexity: O d2k4.5η3.5κ2(V )κ2(Σ)µ(V ) δ3 log n .
  • 5. Notation & quantum information 101 - part 1 Qubit: any unit vector in C2. Basis for this space: |0 = [1, 0]T , |1 = [0, 1]T |ψ = α |0 + β |1 s.t. |α2 | + |β2 | = 1 Tensor product between vectors: [a, b] ⊗ [c, d] = [ac, ad, bc, bd] Quantum state are vectors. Let x ∈ Rd , then: |x = 1 x 2 x = 1 x 2 2n i=1 xi |i Note: |x has log d qubits! Measuring quantum state |x : p(|i ) = x2 i / x 2
  • 6. Notation & quantum information 101 - part 2 A Quantum program is a unitary matrix U |y = U |x Quantum circuit is composed of elementary quantum gates: NOT = 0 1 1 0 H = 1 √ 2 1 1 1 −1 Runtime of quantum algorithm = depth of circuit.
  • 7. Quantum Machine Learning Toolkit 1. Grover-like algorithms 2. Quantum access to classical data 3. Quantum linear algebra 4. Distance estimation 5. Tomography (others: amplification techniques, Hamiltonian simulations, etc..)
  • 8. Grover’s Algorithm Problem: Given a function f : {0, 1}n → {0, 1}, find the only x such that f (x) = 1. Classically: It takes O(2n).
  • 9. Grover’s Algorithm Problem: Given a function f : {0, 1}n → {0, 1}, find the only x such that f (x) = 1. Classically: It takes O(2n). Theorem [Grover algorithm (informal)] There exists an algorithm that finds x such that f (x) = 1 in time O( √ 2n)
  • 10. Quantum access to classical matrices Let V ∈ Rn×d , with vi row of V , 1 V F i vi |i |vi (1)
  • 11. Quantum access to classical matrices Let V ∈ Rn×d , with vi row of V , 1 V F i vi |i |vi (1) Facts: Preparation (preprocessing) time: O(nd log nd) Size: O(nd log nd) Execution time: O(log nd) Can be implemented with a generalization of the QRAM, (PhD thesis of A. Prakash)
  • 12.
  • 13. Quantum linear algebra “Solve” linear systems Ax = b Breakthrough! - HHL algorithm in 2009 Assuming quantum access to matrix A ∈ Rn×d Encode b ∈ Rd as |b We can prepare |A−1b or |Ab , in O µ(A)κ(A) Norm A−1b is estimated with rel. error with additional O(1/ ) time.
  • 14. Distance estimation What: With quantum access to matrices V , C: |i |j |0 → |i |j |d(vi , cj ) distance between row i of V and j of C. Error: relative Time: O η where η = maxi,j ( vi 2 + cj 2 )
  • 15. Tomography Retrieving data from quantum computers For a quantum state |x ∈ Rd we get classical estimate x |x − x 2 ≤ δ by generating |x O d/δ2 times. |x − x ∞ ≤ δ by generating |x O log(d)/δ2 times. Also, sampling, amplitude estimation..
  • 16.
  • 17. Credit: Wikipedia user: Chire (CC BY-SA 3.0)
  • 18. Gaussian mixture models (GMM) Assumption on data (vi , yi ). Is generated by: 1. Sampling a label yi ∈ [k] according to Mult(θ), 2. Sampling a vector vi according to N(µyi , Σyi ). Mult(θ): multinomial distribution (a dice) for θ ∈ Rk N(µyi , Σyi ): multivariate Gaussian distribution GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
  • 19. Gaussian mixture models (GMM) Assumption on data (vi , yi ). Is generated by: 1. Sampling a label yi ∈ [k] according to Mult(θ), 2. Sampling a vector vi according to N(µyi , Σyi ). Mult(θ): multinomial distribution (a dice) for θ ∈ Rk N(µyi , Σyi ): multivariate Gaussian distribution GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk) Robust GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk)
  • 20. Gaussian mixture models (GMM) Assumption on data (vi , yi ). Is generated by: 1. Sampling a label yi ∈ [k] according to Mult(θ), 2. Sampling a vector vi according to N(µyi , Σyi ). Mult(θ): multinomial distribution (a dice) for θ ∈ Rk N(µyi , Σyi ): multivariate Gaussian distribution GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk) Robust GMM Model: γ = (θ, µ1, · · · , µk, Σ1, · · · , Σk) θ − θ ≤ δθ, µj − µj ≤ δµ, Σj − Σj ≤ δµ √ η
  • 21.
  • 22.
  • 23.
  • 24.
  • 25.
  • 26.
  • 27. Classical EM for GMM: O(tndω k) 1: repeat 2: Expectation rt ij = θt j N(vi ; µt j , Σt j ) k l=1 θt l N(vi ; µt l , Σt l ) ∀i ∈ [n], j ∈ [k] 3: Maximization Update the parameters of the model as: θt+1 j ← 1 n n i=1 rt ij µt+1 j ← n i=1 rt ij vi n i=1 rt ij Σt+1 j ← n i=1 rt ij (vi − µt+1 j )(vi − µt+1 j )T n i=1 rt ij 4: t=t+1 5: until | (γt−1; V ) − (γt; V )| < τ
  • 28.
  • 29. Quantum Expectation We want estimate: rij = p(vi |j) We build U |i |j → |i |j |rij and U |j |0 → |j 1 Rj n i rij |i Error: additive Time: ˜O( k1.5ηκ(Σ) δ )
  • 30. Quantum Maximization θt+1 We want: θt+1 j ← 1 n n i=1 rt ij Trick: Use Expectation Step and amplitude amplification to build: | √ R := k j=1 θj t+1 | Rj |j . (2) Error: θ t − θt < δθ Runtime: Tθ = O k3.5 η1.5 κ2(Σ)µ(Σ) δ2 θ log n
  • 31. VoxForge dataset: Speaker recognition Σ 2 |logdet(Σ)| κ∗ (Σ) µ(Σ) µ(V ) κ(V ) MAP avg 0.244 58.56 4.21 3.82 2.14 23.82 max 2.45 70.08 50 4.35 2.79 40.38 ML avg 1.31 14.56 15.57 2.54 2.14 23.82 max 3.44 92,3 50 3.67 2.79 40.38 η = 13 Classical accuracy: 98.8% Quantum accuracy: 98.2% Comparable number of iterations
  • 32. Variational circuits - another paradigm for QML Credit: Dawid Kopczyk
  • 33.
  • 34. De-quantizations Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning -Nai-Hui Chia, Andr´as Gily´en, Tongyang Li, Han-Hsuan Lin, Ewin Tang, Chunhao Wang [1910.06151] Quantum-Inspired Classical Algorithms for Singular Value Transformation - Dhawal Jethwani, Fran¸cois Le Gall, Sanjay K. Singh [1910.05699] ... but also... Arrazola, Juan Miguel, et al. ”Quantum-inspired algorithms in practice.” arXiv preprint [1905.10415] . Dequantized recommandation system’ runtimes: O A 24 F 12σ24
  • 35. Conclusions We made well-clusterability assumptions, ... but we have runtime guarantees on non well-clusterable datasets! We have also quantum initialization strategies! QEM works for all base distributions in exponential family! Faster quantum algorithms for the log-determinant soon! :)