SlideShare a Scribd company logo
1 of 51
Download to read offline
Phase transition for statistical estimation:
algorithms and fundamental limits
Marc Lelarge
INRIA-ENS
APS - INFORMS 2023
A bit of history: 70’s
A bit of history: 70’s
A bit of history: 2010’s
A bit of history: 2010’s
A bit of history: 2010’s
Applications to high-dimensional statistics
Approximate Message Passing
Approximate Message Passing
This tutorial: demystifying statistical physics!
- A simple version of AMP algoritm
This tutorial: demystifying statistical physics!
- A simple version of AMP algoritm
- Gap between information-theoretically optimal and
computationally feasible estimators
This tutorial: demystifying statistical physics!
- A simple version of AMP algoritm
- Gap between information-theoretically optimal and
computationally feasible estimators
- Running example: matrix model
I connection to random matrix theory
I sparse PCA, community detection, Z2 synchronization,
submatrix localization, hidden clique...
AMP and its state evolution
Given a matrix W ∈ Rn×n and scalar functions ft : R → R, let
x0 ∈ Rn and
xt+1
= Wft(xt
) − btft−1(xt−1
) ∈ Rn
where
bt =
1
n
n
X
i=1
f 0
t (xt
i ) ∈ R.
AMP and its state evolution
Given a matrix W ∈ Rn×n and scalar functions ft : R → R, let
x0 ∈ Rn and
xt+1
= Wft(xt
) − btft−1(xt−1
) ∈ Rn
where
bt =
1
n
n
X
i=1
f 0
t (xt
i ) ∈ R.
If W ∼ GOE(n), ft are Lipschitz and the components of x0 are i.i.d
∼ X0 with E

X2
0

= 1, then for any nice test function Ψ : Rt → R,
1
n
n
X
i=1
Ψ

x1
i , . . . , xt
i

→ E [Ψ(Z1, . . . , Zt)] ,
where (Z1, . . . , Zt)
d
= (σ1G1, . . . , σtGt), where Gs ∼ N(0, 1) i.i.d.
(Bayati Montanari ’11)
Sanity check
We have x1 = Wf0(x0) so that
x1
i =
X
j
Wijf0(x0
j ),
where Wij ∼ N(0, 1/n) i.i.d. (ignore diagonal terms).
Hence x1 is a centred Gaussian vector with entries having variance
1
N
X
j
f0(x0
j )2
≈ E
h
f0(X0)2
i
= σ1.
AMP proof of Wigner’s semicircle law
Consider AMP with linear functions ft(x) = x, so that
x1
= Wx0
x2
= Wx1
− x0
= (W2
− Id)x0
x3
= Wx2
− x1
= (W3
− 2W)x0
,
AMP proof of Wigner’s semicircle law
Consider AMP with linear functions ft(x) = x, so that
x1
= Wx0
x2
= Wx1
− x0
= (W2
− Id)x0
x3
= Wx2
− x1
= (W3
− 2W)x0
,
so xt = Pt(W)x0 with
P0(x) = 1, P1(x) = x
Pt+1(x) = xPt(x) − Pt−1(x).
{Pt} are Chebyshev polynomials orthonormal wr.t. the semicircle
density µSC(x) = 1
2π
q
(4 − x2)+.
AMP proof of Wigner’s semicircle law
Consider AMP with linear functions ft(x) = x, so that
x1
= Wx0
x2
= Wx1
− x0
= (W2
− Id)x0
x3
= Wx2
− x1
= (W3
− 2W)x0
,
so xt = Pt(W)x0 with
P0(x) = 1, P1(x) = x
Pt+1(x) = xPt(x) − Pt−1(x).
{Pt} are Chebyshev polynomials orthonormal wr.t. the semicircle
density µSC(x) = 1
2π
q
(4 − x2)+.
When 1
n kx0k = 1, we have 1
n hxs, xti ≈ trPs(W)Pt(Wt).
AMP proof of Wigner’s semicircle law
xt+1
= Wxt
− xt−1
In this case, AMP state evolution gives
1
n
hxs
, xt
i → E [ZsZt] = 1(s = t)
AMP proof of Wigner’s semicircle law
xt+1
= Wxt
− xt−1
In this case, AMP state evolution gives
1
n
hxs
, xt
i → E [ZsZt] = 1(s = t)
Since 1
n hxs, xti ≈ trPs(W)Pt(Wt), the polynomials Pt are
orthonormal w.r.t the limit empirical spectral distribution of W
which must be µSC.
AMP proof of Wigner’s semicircle law
xt+1
= Wxt
− xt−1
In this case, AMP state evolution gives
1
n
hxs
, xt
i → E [ZsZt] = 1(s = t)
Since 1
n hxs, xti ≈ trPs(W)Pt(Wt), the polynomials Pt are
orthonormal w.r.t the limit empirical spectral distribution of W
which must be µSC.
Credit: Zhou Fan.
Wigner’s semicircle law: experiments
Wigner’s semicircle law: experiments
Wigner’s semicircle law: experiments
Wigner’s semicircle law: experiments
Explaining the Onsager term
xt+1
= Wxt
− xt−1
The first iteration with an Onsager term appears for t = 2.
Explaining the Onsager term
xt+1
= Wxt
− xt−1
The first iteration with an Onsager term appears for t = 2.
Then we have x2 = Wx1 − x0 = W2x0 − x0 so that
x2
1 =
X
i
W 2
1i x0
1 +
X
i,j6=1
W1i Wijx0
j − x0
1
=



X
i
W 2
1i x0
1 +
X
i,j6=1
W1i Wijx0
j
| {z }
N(0,1)
−

x0
1
Explaining the Onsager term
xt+1
= Wxt
− xt−1
The first iteration with an Onsager term appears for t = 2.
Then we have x2 = Wx1 − x0 = W2x0 − x0 so that
x2
1 =
X
i
W 2
1i x0
1 +
X
i,j6=1
W1i Wijx0
j − x0
1
=



X
i
W 2
1i x0
1 +
X
i,j6=1
W1i Wijx0
j
| {z }
N(0,1)
−

x0
1
The Onsager term is very similar to the Itô-correction in stochastic
calculus.
This tutorial: demystifying statistical physics!
- A simple version of AMP algoritm
- Gap between information-theoretically optimal and
computationally feasible estimators
- Running example: matrix model
I connection to random matrix theory
I sparse PCA, community detection, Z2 synchronization,
submatrix localization, hidden clique...
Low-rank matrix estimation
“Spiked Wigner” model
Y
|{z}
observations
=
v
u
u
u
t
λ
n
XX|
| {z }
signal
+ Z
|{z}
noise
I X: vector of dimension n with entries Xi
i.i.d.
∼ P0. EX1 = 0,
EX2
1 = 1.
I Zi,j = Zj,i
i.i.d.
∼ N(0, 1).
I λ: signal-to-noise ratio.
I λ and P0 are known by the statistician.
Goal: recover the low-rank matrix XX|
from Y.
Principal component analysis (PCA)
Spectral estimator:
Estimate X using the eigenvector x̂n associated with the
largest eigenvalue µn of Y/
√
n.
Principal component analysis (PCA)
Spectral estimator:
Estimate X using the eigenvector x̂n associated with the
largest eigenvalue µn of Y/
√
n.
B.B.P. phase transition
I if λ 6 1



µn
a.s.
−
−
−
→
n→∞
2
X · x̂n
a.s.
−
−
−
→
n→∞
0
I if λ  1



µn
a.s.
−
−
−
→
n→∞
√
λ + 1
√
λ
 2
|X · x̂n|
a.s.
−
−
−
→
n→∞
p
1 − 1/λ  0
(Baik, Ben Arous, Péché ’05)
Questions
I PCA fails when λ 6 1, but is it still possible to recover
the signal?
Questions
I PCA fails when λ 6 1, but is it still possible to recover
the signal?
I When λ  1, is PCA optimal?
Questions
I PCA fails when λ 6 1, but is it still possible to recover
the signal?
I When λ  1, is PCA optimal?
I More generally, what is the best achievable estimation
performance in both regimes?
Plot of MMSE
Figure: Spiked Wigner model, centred binary prior (unit variance).
We can certainly improve spectral algorithm!
A scalar denoising problem
For Y =
√
γX0 + Z where X0 ∼ P0 and Z ∼ N(0, 1)
A scalar denoising problem
For Y =
√
γX0 + Z where X0 ∼ P0 and Z ∼ N(0, 1)
Bayes optimal AMP
We define mmse(γ) = E
h
X0 − E[X0|
√
γX0 + Z]
2
i
and the
recursion:
q0 = 1 − λ−1
qt+1 = 1 − mmse(λqt).
With the optimal denoiser gP0 (y, γ) = E[X0|
√
γX0 + Z = y], AMP
is defined by:
xt+1
= Y
s
λ
n
ft(xt
) − λbtft−1(xt−1
),
where ft(y) = gP0 (y/
√
λqt, λqt).
Bayes optimal AMP: experiment
Plot of MMSE
Figure: Spiked Wigner model, centred binary prior (unit variance).
Plot of MMSE
Figure: Spiked Wigner model, centred binary prior (unit variance).
Limiting formula for the MMSE
Theorem (L, Miolane ’19)
MMSEn −
−
−
→
n→∞
1
|{z}
Dummy MSE
− q∗
(λ)2
where q∗
(λ) is the minimizer of
q  0 7→ −EX0∼P0
Z0∼N

log
Z
x0
dP0(x0)e
√
λqZ0x0+λqX0x0+λq
2
x2
0

+
λ
4
q2
A simplified “free energy landscape”:
0.0 0.2 0.4 0.6 0.8 1.0
q
−0.06
−0.05
−0.04
−0.03
−0.02
−0.01
0.00 −F(λ, q)
(a) “Easy” phase (λ = 1.01)
0.0 0.2 0.4 0.6 0.8
q
−0.002
−0.001
0.000
0.001
0.002
0.003
−F(λ, q)
(b) “Hard” phase (λ = 0.625)
0.0 0.2 0.4 0.6 0.8
q
0.0000
0.0025
0.0050
0.0075
0.0100
0.0125
0.0150
0.0175 −F(λ, q)
(c) “Impossible” phase (λ = 0.5)
Phase diagram
Figure: Spiked Wigner model, centred binary prior (unit variance).
Proof ideas: a planted spin system
P(X = x | Y) =
1
Zn
P0(x)eHn(x)
where
Hn(x) =
X
ij
s
λ
n
Yi,jxi xj −
λ
2n
x2
i x2
j .
Proof ideas: a planted spin system
P(X = x | Y) =
1
Zn
P0(x)eHn(x)
where
Hn(x) =
X
ij
s
λ
n
Yi,jxi xj −
λ
2n
x2
i x2
j .
Two step proof:
I Lower bound: Guerra’s interpolation technique. Adapted in
(Korada, Macris ’09) (Krzakala, Xu, Zdeborová ’16)
(
Y =
√
t
p
λ/n XX| + Z
Y0 =
√
1 − t
√
λ X + Z0
I Upper bound: Cavity computations (Mézard, Parisi, Virasoro
’87). Aizenman-Sims-Starr scheme:(Aizenman, Sims,Starr
’03) (Talagrand ’10)
Conclusion
AMP is an iterative denoising algorithm which is optimal when the
energy landscape is simple.
Main references for this tutorial: (Montanari Venkataramanan ’21)
(L. Miolane ’19)
Many recent research directions: universality, structured matrices,
composition... and new applications outside electrical engineering
like in ecology.
Conclusion
AMP is an iterative denoising algorithm which is optimal when the
energy landscape is simple.
Main references for this tutorial: (Montanari Venkataramanan ’21)
(L. Miolane ’19)
Many recent research directions: universality, structured matrices,
composition... and new applications outside electrical engineering
like in ecology.
Deep learning, the new kid on the block:
Thank you for your attention !

More Related Content

What's hot

Applied numerical methods lec11
Applied numerical methods lec11Applied numerical methods lec11
Applied numerical methods lec11Yasser Ahmed
 
algebric solutions by newton raphson method and secant method
algebric solutions by newton raphson method and secant methodalgebric solutions by newton raphson method and secant method
algebric solutions by newton raphson method and secant methodNagma Modi
 
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...Waqas Afzal
 
fourier series
fourier seriesfourier series
fourier series8laddu8
 
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier Analysis
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier AnalysisDSP_FOEHU - MATLAB 02 - The Discrete-time Fourier Analysis
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier AnalysisAmr E. Mohamed
 
Processing Semantically-Ordered Streams in Financial Services
Processing Semantically-Ordered Streams in Financial ServicesProcessing Semantically-Ordered Streams in Financial Services
Processing Semantically-Ordered Streams in Financial ServicesFlink Forward
 
Fractional Calculus PP
Fractional Calculus PPFractional Calculus PP
Fractional Calculus PPVRRITC
 
Linear transformation and application
Linear transformation and applicationLinear transformation and application
Linear transformation and applicationshreyansp
 
Langrange Interpolation Polynomials
Langrange Interpolation PolynomialsLangrange Interpolation Polynomials
Langrange Interpolation PolynomialsSohaib H. Khan
 
Simulating communication systems with MATLAB: An introduction
Simulating communication systems with MATLAB: An introductionSimulating communication systems with MATLAB: An introduction
Simulating communication systems with MATLAB: An introductionAniruddha Chandra
 
Laplace transforms
Laplace transformsLaplace transforms
Laplace transformsKarnav Rana
 
Best Practices in Creating a Strategic Finance Function
Best Practices in Creating a Strategic Finance FunctionBest Practices in Creating a Strategic Finance Function
Best Practices in Creating a Strategic Finance FunctionFindWhitePapers
 
Taylor and maclaurian series
Taylor and maclaurian seriesTaylor and maclaurian series
Taylor and maclaurian seriesNishant Patel
 
NOAH19 London Investor Book
NOAH19 London Investor BookNOAH19 London Investor Book
NOAH19 London Investor BookNOAH Advisors
 

What's hot (20)

Runge kutta 2nd Order
Runge kutta 2nd OrderRunge kutta 2nd Order
Runge kutta 2nd Order
 
Applied numerical methods lec11
Applied numerical methods lec11Applied numerical methods lec11
Applied numerical methods lec11
 
algebric solutions by newton raphson method and secant method
algebric solutions by newton raphson method and secant methodalgebric solutions by newton raphson method and secant method
algebric solutions by newton raphson method and secant method
 
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...
laplace transform and inverse laplace, properties, Inverse Laplace Calculatio...
 
fourier series
fourier seriesfourier series
fourier series
 
Partial derivatives
Partial derivativesPartial derivatives
Partial derivatives
 
Properties of z transform day 2
Properties of z transform day 2Properties of z transform day 2
Properties of z transform day 2
 
FPDE presentation
FPDE presentationFPDE presentation
FPDE presentation
 
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier Analysis
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier AnalysisDSP_FOEHU - MATLAB 02 - The Discrete-time Fourier Analysis
DSP_FOEHU - MATLAB 02 - The Discrete-time Fourier Analysis
 
Processing Semantically-Ordered Streams in Financial Services
Processing Semantically-Ordered Streams in Financial ServicesProcessing Semantically-Ordered Streams in Financial Services
Processing Semantically-Ordered Streams in Financial Services
 
Fractional Calculus PP
Fractional Calculus PPFractional Calculus PP
Fractional Calculus PP
 
Linear transformation and application
Linear transformation and applicationLinear transformation and application
Linear transformation and application
 
Z transform
Z transformZ transform
Z transform
 
Langrange Interpolation Polynomials
Langrange Interpolation PolynomialsLangrange Interpolation Polynomials
Langrange Interpolation Polynomials
 
Simulating communication systems with MATLAB: An introduction
Simulating communication systems with MATLAB: An introductionSimulating communication systems with MATLAB: An introduction
Simulating communication systems with MATLAB: An introduction
 
Laplace transforms
Laplace transformsLaplace transforms
Laplace transforms
 
Best Practices in Creating a Strategic Finance Function
Best Practices in Creating a Strategic Finance FunctionBest Practices in Creating a Strategic Finance Function
Best Practices in Creating a Strategic Finance Function
 
Taylor and maclaurian series
Taylor and maclaurian seriesTaylor and maclaurian series
Taylor and maclaurian series
 
Fourier series
Fourier seriesFourier series
Fourier series
 
NOAH19 London Investor Book
NOAH19 London Investor BookNOAH19 London Investor Book
NOAH19 London Investor Book
 

Similar to Tutorial APS 2023: Phase transition for statistical estimation: algorithms and fundamental limits.

Mathematics and AI
Mathematics and AIMathematics and AI
Mathematics and AIMarc Lelarge
 
MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsElvis DOHMATOB
 
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
 
Introduction to Diffusion Monte Carlo
Introduction to Diffusion Monte CarloIntroduction to Diffusion Monte Carlo
Introduction to Diffusion Monte CarloClaudio Attaccalite
 
Neuronal self-organized criticality
Neuronal self-organized criticalityNeuronal self-organized criticality
Neuronal self-organized criticalityOsame Kinouchi
 
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...Yandex
 
comm_ch02_random_en.pdf
comm_ch02_random_en.pdfcomm_ch02_random_en.pdf
comm_ch02_random_en.pdfssuser87c04b
 
Low Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse ProblemsLow Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse ProblemsGabriel Peyré
 
Ph 101-9 QUANTUM MACHANICS
Ph 101-9 QUANTUM MACHANICSPh 101-9 QUANTUM MACHANICS
Ph 101-9 QUANTUM MACHANICSChandan Singh
 
On Application of Power Series Solution of Bessel Problems to the Problems of...
On Application of Power Series Solution of Bessel Problems to the Problems of...On Application of Power Series Solution of Bessel Problems to the Problems of...
On Application of Power Series Solution of Bessel Problems to the Problems of...BRNSS Publication Hub
 
Introduction to Quantum Monte Carlo
Introduction to Quantum Monte CarloIntroduction to Quantum Monte Carlo
Introduction to Quantum Monte CarloClaudio Attaccalite
 
MCMC and likelihood-free methods
MCMC and likelihood-free methodsMCMC and likelihood-free methods
MCMC and likelihood-free methodsChristian Robert
 

Similar to Tutorial APS 2023: Phase transition for statistical estimation: algorithms and fundamental limits. (20)

Mathematics and AI
Mathematics and AIMathematics and AI
Mathematics and AI
 
MVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priorsMVPA with SpaceNet: sparse structured priors
MVPA with SpaceNet: sparse structured priors
 
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
 
Introduction to Diffusion Monte Carlo
Introduction to Diffusion Monte CarloIntroduction to Diffusion Monte Carlo
Introduction to Diffusion Monte Carlo
 
Neuronal self-organized criticality
Neuronal self-organized criticalityNeuronal self-organized criticality
Neuronal self-organized criticality
 
AJMS_389_22.pdf
AJMS_389_22.pdfAJMS_389_22.pdf
AJMS_389_22.pdf
 
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...
Subgradient Methods for Huge-Scale Optimization Problems - Юрий Нестеров, Cat...
 
comm_ch02_random_en.pdf
comm_ch02_random_en.pdfcomm_ch02_random_en.pdf
comm_ch02_random_en.pdf
 
Jere Koskela slides
Jere Koskela slidesJere Koskela slides
Jere Koskela slides
 
Probable
ProbableProbable
Probable
 
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
 
5.n nmodels i
5.n nmodels i5.n nmodels i
5.n nmodels i
 
Low Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse ProblemsLow Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
Low Complexity Regularization of Inverse Problems - Course #1 Inverse Problems
 
Ph 101-9 QUANTUM MACHANICS
Ph 101-9 QUANTUM MACHANICSPh 101-9 QUANTUM MACHANICS
Ph 101-9 QUANTUM MACHANICS
 
On Application of Power Series Solution of Bessel Problems to the Problems of...
On Application of Power Series Solution of Bessel Problems to the Problems of...On Application of Power Series Solution of Bessel Problems to the Problems of...
On Application of Power Series Solution of Bessel Problems to the Problems of...
 
PCA on graph/network
PCA on graph/networkPCA on graph/network
PCA on graph/network
 
03_AJMS_209_19_RA.pdf
03_AJMS_209_19_RA.pdf03_AJMS_209_19_RA.pdf
03_AJMS_209_19_RA.pdf
 
03_AJMS_209_19_RA.pdf
03_AJMS_209_19_RA.pdf03_AJMS_209_19_RA.pdf
03_AJMS_209_19_RA.pdf
 
Introduction to Quantum Monte Carlo
Introduction to Quantum Monte CarloIntroduction to Quantum Monte Carlo
Introduction to Quantum Monte Carlo
 
MCMC and likelihood-free methods
MCMC and likelihood-free methodsMCMC and likelihood-free methods
MCMC and likelihood-free methods
 

Recently uploaded

Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxNandakishor Bhaurao Deshmukh
 
‏‏VIRUS - 123455555555555555555555555555555555555555
‏‏VIRUS -  123455555555555555555555555555555555555555‏‏VIRUS -  123455555555555555555555555555555555555555
‏‏VIRUS - 123455555555555555555555555555555555555555kikilily0909
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024AyushiRastogi48
 
TOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsTOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsssuserddc89b
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett SquareIsiahStephanRadaza
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxFarihaAbdulRasheed
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxVarshiniMK
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |aasikanpl
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzohaibmir069
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsHajira Mahmood
 
Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10ROLANARIBATO3
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...lizamodels9
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫qfactory1
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)DHURKADEVIBASKAR
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Masticationvidulajaib
 
Speech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxSpeech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxpriyankatabhane
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsCharlene Llagas
 

Recently uploaded (20)

Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptxTHE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
THE ROLE OF PHARMACOGNOSY IN TRADITIONAL AND MODERN SYSTEM OF MEDICINE.pptx
 
‏‏VIRUS - 123455555555555555555555555555555555555555
‏‏VIRUS -  123455555555555555555555555555555555555555‏‏VIRUS -  123455555555555555555555555555555555555555
‏‏VIRUS - 123455555555555555555555555555555555555555
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024Vision and reflection on Mining Software Repositories research in 2024
Vision and reflection on Mining Software Repositories research in 2024
 
TOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physicsTOPIC 8 Temperature and Heat.pdf physics
TOPIC 8 Temperature and Heat.pdf physics
 
Module 4: Mendelian Genetics and Punnett Square
Module 4:  Mendelian Genetics and Punnett SquareModule 4:  Mendelian Genetics and Punnett Square
Module 4: Mendelian Genetics and Punnett Square
 
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptxRESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
RESPIRATORY ADAPTATIONS TO HYPOXIA IN HUMNAS.pptx
 
Cytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptxCytokinin, mechanism and its application.pptx
Cytokinin, mechanism and its application.pptx
 
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Hauz Khas Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Lajpat Nagar (Delhi) |
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistan
 
Solution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutionsSolution chemistry, Moral and Normal solutions
Solution chemistry, Moral and Normal solutions
 
Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10Gas_Laws_powerpoint_notes.ppt for grade 10
Gas_Laws_powerpoint_notes.ppt for grade 10
 
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
Best Call Girls In Sector 29 Gurgaon❤️8860477959 EscorTs Service In 24/7 Delh...
 
Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫Manassas R - Parkside Middle School 🌎🏫
Manassas R - Parkside Middle School 🌎🏫
 
Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)Recombinant DNA technology( Transgenic plant and animal)
Recombinant DNA technology( Transgenic plant and animal)
 
Temporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of MasticationTemporomandibular joint Muscles of Mastication
Temporomandibular joint Muscles of Mastication
 
Speech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptxSpeech, hearing, noise, intelligibility.pptx
Speech, hearing, noise, intelligibility.pptx
 
Heredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of TraitsHeredity: Inheritance and Variation of Traits
Heredity: Inheritance and Variation of Traits
 

Tutorial APS 2023: Phase transition for statistical estimation: algorithms and fundamental limits.

  • 1. Phase transition for statistical estimation: algorithms and fundamental limits Marc Lelarge INRIA-ENS APS - INFORMS 2023
  • 2. A bit of history: 70’s
  • 3. A bit of history: 70’s
  • 4. A bit of history: 2010’s
  • 5. A bit of history: 2010’s
  • 6. A bit of history: 2010’s
  • 10. This tutorial: demystifying statistical physics! - A simple version of AMP algoritm
  • 11. This tutorial: demystifying statistical physics! - A simple version of AMP algoritm - Gap between information-theoretically optimal and computationally feasible estimators
  • 12. This tutorial: demystifying statistical physics! - A simple version of AMP algoritm - Gap between information-theoretically optimal and computationally feasible estimators - Running example: matrix model I connection to random matrix theory I sparse PCA, community detection, Z2 synchronization, submatrix localization, hidden clique...
  • 13.
  • 14. AMP and its state evolution Given a matrix W ∈ Rn×n and scalar functions ft : R → R, let x0 ∈ Rn and xt+1 = Wft(xt ) − btft−1(xt−1 ) ∈ Rn where bt = 1 n n X i=1 f 0 t (xt i ) ∈ R.
  • 15. AMP and its state evolution Given a matrix W ∈ Rn×n and scalar functions ft : R → R, let x0 ∈ Rn and xt+1 = Wft(xt ) − btft−1(xt−1 ) ∈ Rn where bt = 1 n n X i=1 f 0 t (xt i ) ∈ R. If W ∼ GOE(n), ft are Lipschitz and the components of x0 are i.i.d ∼ X0 with E X2 0 = 1, then for any nice test function Ψ : Rt → R, 1 n n X i=1 Ψ x1 i , . . . , xt i → E [Ψ(Z1, . . . , Zt)] , where (Z1, . . . , Zt) d = (σ1G1, . . . , σtGt), where Gs ∼ N(0, 1) i.i.d. (Bayati Montanari ’11)
  • 16. Sanity check We have x1 = Wf0(x0) so that x1 i = X j Wijf0(x0 j ), where Wij ∼ N(0, 1/n) i.i.d. (ignore diagonal terms). Hence x1 is a centred Gaussian vector with entries having variance 1 N X j f0(x0 j )2 ≈ E h f0(X0)2 i = σ1.
  • 17. AMP proof of Wigner’s semicircle law Consider AMP with linear functions ft(x) = x, so that x1 = Wx0 x2 = Wx1 − x0 = (W2 − Id)x0 x3 = Wx2 − x1 = (W3 − 2W)x0 ,
  • 18. AMP proof of Wigner’s semicircle law Consider AMP with linear functions ft(x) = x, so that x1 = Wx0 x2 = Wx1 − x0 = (W2 − Id)x0 x3 = Wx2 − x1 = (W3 − 2W)x0 , so xt = Pt(W)x0 with P0(x) = 1, P1(x) = x Pt+1(x) = xPt(x) − Pt−1(x). {Pt} are Chebyshev polynomials orthonormal wr.t. the semicircle density µSC(x) = 1 2π q (4 − x2)+.
  • 19. AMP proof of Wigner’s semicircle law Consider AMP with linear functions ft(x) = x, so that x1 = Wx0 x2 = Wx1 − x0 = (W2 − Id)x0 x3 = Wx2 − x1 = (W3 − 2W)x0 , so xt = Pt(W)x0 with P0(x) = 1, P1(x) = x Pt+1(x) = xPt(x) − Pt−1(x). {Pt} are Chebyshev polynomials orthonormal wr.t. the semicircle density µSC(x) = 1 2π q (4 − x2)+. When 1 n kx0k = 1, we have 1 n hxs, xti ≈ trPs(W)Pt(Wt).
  • 20. AMP proof of Wigner’s semicircle law xt+1 = Wxt − xt−1 In this case, AMP state evolution gives 1 n hxs , xt i → E [ZsZt] = 1(s = t)
  • 21. AMP proof of Wigner’s semicircle law xt+1 = Wxt − xt−1 In this case, AMP state evolution gives 1 n hxs , xt i → E [ZsZt] = 1(s = t) Since 1 n hxs, xti ≈ trPs(W)Pt(Wt), the polynomials Pt are orthonormal w.r.t the limit empirical spectral distribution of W which must be µSC.
  • 22. AMP proof of Wigner’s semicircle law xt+1 = Wxt − xt−1 In this case, AMP state evolution gives 1 n hxs , xt i → E [ZsZt] = 1(s = t) Since 1 n hxs, xti ≈ trPs(W)Pt(Wt), the polynomials Pt are orthonormal w.r.t the limit empirical spectral distribution of W which must be µSC. Credit: Zhou Fan.
  • 27. Explaining the Onsager term xt+1 = Wxt − xt−1 The first iteration with an Onsager term appears for t = 2.
  • 28. Explaining the Onsager term xt+1 = Wxt − xt−1 The first iteration with an Onsager term appears for t = 2. Then we have x2 = Wx1 − x0 = W2x0 − x0 so that x2 1 = X i W 2 1i x0 1 + X i,j6=1 W1i Wijx0 j − x0 1 = X i W 2 1i x0 1 + X i,j6=1 W1i Wijx0 j | {z } N(0,1) − x0 1
  • 29. Explaining the Onsager term xt+1 = Wxt − xt−1 The first iteration with an Onsager term appears for t = 2. Then we have x2 = Wx1 − x0 = W2x0 − x0 so that x2 1 = X i W 2 1i x0 1 + X i,j6=1 W1i Wijx0 j − x0 1 = X i W 2 1i x0 1 + X i,j6=1 W1i Wijx0 j | {z } N(0,1) − x0 1 The Onsager term is very similar to the Itô-correction in stochastic calculus.
  • 30. This tutorial: demystifying statistical physics! - A simple version of AMP algoritm - Gap between information-theoretically optimal and computationally feasible estimators - Running example: matrix model I connection to random matrix theory I sparse PCA, community detection, Z2 synchronization, submatrix localization, hidden clique...
  • 31. Low-rank matrix estimation “Spiked Wigner” model Y |{z} observations = v u u u t λ n XX| | {z } signal + Z |{z} noise I X: vector of dimension n with entries Xi i.i.d. ∼ P0. EX1 = 0, EX2 1 = 1. I Zi,j = Zj,i i.i.d. ∼ N(0, 1). I λ: signal-to-noise ratio. I λ and P0 are known by the statistician. Goal: recover the low-rank matrix XX| from Y.
  • 32. Principal component analysis (PCA) Spectral estimator: Estimate X using the eigenvector x̂n associated with the largest eigenvalue µn of Y/ √ n.
  • 33. Principal component analysis (PCA) Spectral estimator: Estimate X using the eigenvector x̂n associated with the largest eigenvalue µn of Y/ √ n. B.B.P. phase transition I if λ 6 1    µn a.s. − − − → n→∞ 2 X · x̂n a.s. − − − → n→∞ 0 I if λ 1    µn a.s. − − − → n→∞ √ λ + 1 √ λ 2 |X · x̂n| a.s. − − − → n→∞ p 1 − 1/λ 0 (Baik, Ben Arous, Péché ’05)
  • 34. Questions I PCA fails when λ 6 1, but is it still possible to recover the signal?
  • 35. Questions I PCA fails when λ 6 1, but is it still possible to recover the signal? I When λ 1, is PCA optimal?
  • 36. Questions I PCA fails when λ 6 1, but is it still possible to recover the signal? I When λ 1, is PCA optimal? I More generally, what is the best achievable estimation performance in both regimes?
  • 37. Plot of MMSE Figure: Spiked Wigner model, centred binary prior (unit variance).
  • 38. We can certainly improve spectral algorithm!
  • 39. A scalar denoising problem For Y = √ γX0 + Z where X0 ∼ P0 and Z ∼ N(0, 1)
  • 40. A scalar denoising problem For Y = √ γX0 + Z where X0 ∼ P0 and Z ∼ N(0, 1)
  • 41. Bayes optimal AMP We define mmse(γ) = E h X0 − E[X0| √ γX0 + Z] 2 i and the recursion: q0 = 1 − λ−1 qt+1 = 1 − mmse(λqt). With the optimal denoiser gP0 (y, γ) = E[X0| √ γX0 + Z = y], AMP is defined by: xt+1 = Y s λ n ft(xt ) − λbtft−1(xt−1 ), where ft(y) = gP0 (y/ √ λqt, λqt).
  • 42. Bayes optimal AMP: experiment
  • 43. Plot of MMSE Figure: Spiked Wigner model, centred binary prior (unit variance).
  • 44. Plot of MMSE Figure: Spiked Wigner model, centred binary prior (unit variance).
  • 45. Limiting formula for the MMSE Theorem (L, Miolane ’19) MMSEn − − − → n→∞ 1 |{z} Dummy MSE − q∗ (λ)2 where q∗ (λ) is the minimizer of q 0 7→ −EX0∼P0 Z0∼N log Z x0 dP0(x0)e √ λqZ0x0+λqX0x0+λq 2 x2 0 + λ 4 q2 A simplified “free energy landscape”: 0.0 0.2 0.4 0.6 0.8 1.0 q −0.06 −0.05 −0.04 −0.03 −0.02 −0.01 0.00 −F(λ, q) (a) “Easy” phase (λ = 1.01) 0.0 0.2 0.4 0.6 0.8 q −0.002 −0.001 0.000 0.001 0.002 0.003 −F(λ, q) (b) “Hard” phase (λ = 0.625) 0.0 0.2 0.4 0.6 0.8 q 0.0000 0.0025 0.0050 0.0075 0.0100 0.0125 0.0150 0.0175 −F(λ, q) (c) “Impossible” phase (λ = 0.5)
  • 46. Phase diagram Figure: Spiked Wigner model, centred binary prior (unit variance).
  • 47. Proof ideas: a planted spin system P(X = x | Y) = 1 Zn P0(x)eHn(x) where Hn(x) = X ij s λ n Yi,jxi xj − λ 2n x2 i x2 j .
  • 48. Proof ideas: a planted spin system P(X = x | Y) = 1 Zn P0(x)eHn(x) where Hn(x) = X ij s λ n Yi,jxi xj − λ 2n x2 i x2 j . Two step proof: I Lower bound: Guerra’s interpolation technique. Adapted in (Korada, Macris ’09) (Krzakala, Xu, Zdeborová ’16) ( Y = √ t p λ/n XX| + Z Y0 = √ 1 − t √ λ X + Z0 I Upper bound: Cavity computations (Mézard, Parisi, Virasoro ’87). Aizenman-Sims-Starr scheme:(Aizenman, Sims,Starr ’03) (Talagrand ’10)
  • 49. Conclusion AMP is an iterative denoising algorithm which is optimal when the energy landscape is simple. Main references for this tutorial: (Montanari Venkataramanan ’21) (L. Miolane ’19) Many recent research directions: universality, structured matrices, composition... and new applications outside electrical engineering like in ecology.
  • 50. Conclusion AMP is an iterative denoising algorithm which is optimal when the energy landscape is simple. Main references for this tutorial: (Montanari Venkataramanan ’21) (L. Miolane ’19) Many recent research directions: universality, structured matrices, composition... and new applications outside electrical engineering like in ecology. Deep learning, the new kid on the block:
  • 51. Thank you for your attention !