Structured signal recovery from non-linear and heavy-tailed measurements

Size: px
Start display at page:

Download "Structured signal recovery from non-linear and heavy-tailed measurements"

Transcription

1 Structured signal recovery from non-linear and heavy-tailed measurements Larry Goldstein* Stanislav Minsker* Xiaohan Wei # *Department of Mathematics # Department of Electrical Engineering UniversityofSouthern California

2 Problem Formulation Single index model: y = f x, θ + δ

3 Problem Formulation Single index model: y = f x, θ + δ x R - random measurement vector;

4 Problem Formulation Single index model: y = f x, θ + δ x R - random measurement vector; δ R random unknown noise independent of x.

5 Problem Formulation Single index model: y = f x, θ + δ x R - random measurement vector; δ R random unknown noise independent of x. θ R - fixed unit unknown vector, d is potentially very large and θ may have certain low dimensional structure.

6 Problem Formulation Single index model: y = f x, θ + δ x R - random measurement vector; δ R random unknown noise independent of x. θ R - fixed unit unknown vector, d is potentially very large and θ may have certain low dimensional structure. f: R R unknown link function.

7 Problem Formulation Single index model: y = f x, θ + δ x R - random measurement vector; δ R random unknown noise independent of x. θ R - fixed unit unknown vector, d is potentially very large and θ may have certain low dimensional structure. f: R R unknown link function. Goal: Estimate θ from i.i.d. sample x J, y J JKL M.

8 Previous Approach If we are only interested in estimating θ, then, solving Least-squares!

9 Previous Approach If we are only interested in estimating θ, then, solving Least-squares! M θn = argmin O P Q y R x J, θ JKL T

10 Previous Approach If we are only interested in estimating θ, then, solving Least-squares! θn = argmin O P Q y R x J, θ x J is Gaussian and Θ R -. M JKL T

11 Previous Approach If we are only interested in estimating θ, then, solving Least-squares! θn = argmin O P Q y R x J, θ x J is Gaussian and Θ R -. M JKL [Brillinger, 1982]; [Plan and Vershynin, 2016]. T

12 Previous Approach Suppose x J are Gaussian and m d, then, with high probability, θn θ T d m

13 Previous Approach Suppose x J are Gaussian and m d, then, with high probability, θn θ T d m Suppose θ is k-sparse, m k log d k, then, with high probability, θn θ T k log (d k) m

14 An example in signal processing:

15 An example in signal processing: One-bit compressed sensing: y J = sign x J, θ, i = 1,2,, m θ is a k-sparse vector, θ T = 1.

16 An example in signal processing: One-bit compressed sensing: y J = sign x J, θ, i = 1,2,, m θ is a k-sparse vector, θ T = 1. Solve: min y R x J, θ T M JKL s.t. θ L θ L

17 An example in signal processing: Geometric intuition: (Picture from

18 An example in signal processing: Geometric intuition: (Picture from

19 Can we always recover θ?

20 Can we always recover θ? The distribution of the measurement vector x is important!

21 Can we always recover θ? The distribution of the measurement vector x is important! Breaks down when x J are Bernoulli 1,1.

22 Can we always recover θ? The distribution of the measurement vector x is important! Breaks down when x J are Bernoulli 1,1. θ L = 1 L 0 0 T θ T = 1 L 0 0 T

23 Can we always recover θ? The distribution of the measurement vector x is important! Breaks down when x J are Bernoulli 1,1. θ L = 1 L 0 0 T θ T = 1 L 0 0 T sign x J, θ L = sign( x J, θ T ) for any x J!

24 Beyond Gaussian distribution

25 Beyond Gaussian distribution Let x N(0, Σ).

26 Beyond Gaussian distribution Let x N(0, Σ). Another way of writing Gaussian: (Σ = BB k ) x = χ T BU.

27 Beyond Gaussian distribution Let x N(0, Σ). Another way of writing Gaussian: (Σ = BB k ) x = χ T BU.

28 Beyond Gaussian distribution Let x N(0, Σ). Another way of writing Gaussian: (Σ = BB k ) x = χ T BU. x = μbu

29 Beyond Gaussian distribution Let x N(0, Σ). Another way of writing Gaussian: (Σ = BB k ) x = χ T BU. x = μbu (centered) Elliptical distribution

30 Why elliptical distribution works? Lemma 1: Let x be elliptical, [Li and Duan, 1991] θ argmin O P E[ y x, θ T ]

31 Finite sample guarantee

32 Finite sample guarantee Difficulty:

33 Finite sample guarantee Difficulty: y = f x, θ + δ

34 Finite sample guarantee Difficulty: y = f x, θ + δ 1. The elliptical distribution of x = μbu can be heavy-tailed.

35 Finite sample guarantee Difficulty: y = f x, θ + δ 1. The elliptical distribution of x = μbu can be heavy-tailed. 2. The noise δ can also be heavy-tailed.

36 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

37 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

38 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

39 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

40 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

41 Goal: Find argmin E[ y x, θ T ] θ T T 2E[y x, θ ] (assuming B = I) θ T T T M y M JKL J x J, θ θ T T T M y M JKL J μ J U J, θ θ T T T M U M JKL J, θ ( μ J y J T) sign(μ J y J )

42 Let q J = ( μ J y J T) sign(μ J y J ) The robust (constrained) estimator: M θn = argmin O P θ T T 2 m Q U J, θ q J The robust (unconstrained) estimator: M JKL θn ƒ = argmin θ T T 2 m Q U J, θ q J JKL + λ θ

43 Theorem 1. Suppose for some κ > 0, Set T = m Œ Ž, E x Tˆ, E δ Tˆ <. Pr θn θ T C L βω Θ m where ω Θ =E š(,œ) sup g, θ. O P,žO Œ Corollary 1: When θ is k-sparse, C T e /T θn θ T (-/ ) M

44 Theorem 1. Suppose for some κ > 0, Set T = m Œ Ž, E x Tˆ, E δ Tˆ <. Pr θn θ T C L βω Θ m where ω Θ =E š(,œ) sup g, θ. O P,žO Œ C T e /T Corollary 1: When θ is k-sparse, with high probability, θn θ T (-/ ) M

45 Theorem 2. Set T = m Œ Ž and λ M, with high probability θn ƒ θ T λ Ψ(S T (ηθ, K)) where G = θ R - : θ 1, and Ψ(S T (ηθ, K)) is a restricted compatibility constant for. Corollary 2: When θ is k-sparse, θn θ T (-) M

46 Theorem 2. Set T = m Œ Ž and λ M, with high probability θn ƒ θ T λ Ψ(S T (ηθ, K)) where G = θ R - : θ 1, and Ψ(S T (ηθ, K)) is a restricted compatibility constant for. Corollary 2: When θ is k-sparse, with high probability, θn ƒ θ T (-) M

47 Corollary 3: When d = d L d T, θ R - Œ -, and θ has rank r, with high probability, and θn θ T r d L + d T m θn ƒ θ T r d L + d T m,,

48 Low computational complexity When θ is k-sparse, the estimator is θ = argmin θ T T 2 b, θ + λ θ L, b = 2 m Q U J q J. A closed form solution: (Soft-thresholding) b J λ 2, b J λ 2, M JKL θ J = 0, λ 2 b J λ 2, b J + λ 2, b J λ 2.

49 Low computational complexity When θ is k-sparse, the estimator is θ± ƒ = argmin θ T T 2 b, θ + λ θ L, b = 1 m Q U J q J. A closed form solution: (Soft-thresholding) b J λ 2, b J λ 2, M JKL θ J = 0, λ 2 b J λ 2, b J + λ 2, b J λ 2.

50 Low computational complexity When θ is k-sparse, the estimator is θ± ƒ = argmin θ T T 2 b, θ + λ θ L, b = 1 m Q U J q J. A closed form solution: (Soft-thresholding) b J λ 2, b J λ 2, M JKL θ J = 0, λ 2 b J λ 2, b J + λ 2, b J λ 2.

51 Simulation: Noiseless One-bit d = 512, m = 128, k = 5 E μ T.L <

52 Simulation: Noisy One-bit (SNR = 10dB) d = 512, m = 128, k = 5 E μ T.L <

53 LS estimator: θ T T 2E[y x, θ ] Markov inequality Truncated LS estimator: θ T T E[ q U, θ ] Generic chaining with customized bounds Empirical estimator: θ T T T M q M JKL J U J, θ

54 LS estimator: θ T T 2E[y x, θ ] Truncated LS estimator: θ T T 2E[ q U, θ ] Empirical estimator: θ T T T M q J U J, θ M JKL

55 LS estimator: θ T T 2E[y x, θ ] Truncated LS estimator: θ T T 2E[ q U, θ ] Empirical estimator: θ T T T M q J U J, θ M JKL

56 LS estimator: θ T T 2E[y x, θ ] Markov inequality Truncated LS estimator: θ T T 2E[ q U, θ ] Generic chaining with customized bounds Empirical estimator: θ T T T M q M JKL J U J, θ

57 Thank you!

sparse and low-rank tensor recovery Cubic-Sketching

sparse and low-rank tensor recovery Cubic-Sketching Sparse and Low-Ran Tensor Recovery via Cubic-Setching Guang Cheng Department of Statistics Purdue University www.science.purdue.edu/bigdata CCAM@Purdue Math Oct. 27, 2017 Joint wor with Botao Hao and Anru

More information

arxiv: v1 [cs.it] 21 Feb 2013

arxiv: v1 [cs.it] 21 Feb 2013 q-ary Compressive Sensing arxiv:30.568v [cs.it] Feb 03 Youssef Mroueh,, Lorenzo Rosasco, CBCL, CSAIL, Massachusetts Institute of Technology LCSL, Istituto Italiano di Tecnologia and IIT@MIT lab, Istituto

More information

Sparse Proteomics Analysis (SPA)

Sparse Proteomics Analysis (SPA) Sparse Proteomics Analysis (SPA) Toward a Mathematical Theory for Feature Selection from Forward Models Martin Genzel Technische Universität Berlin Winter School on Compressed Sensing December 5, 2015

More information

Greedy Signal Recovery and Uniform Uncertainty Principles

Greedy Signal Recovery and Uniform Uncertainty Principles Greedy Signal Recovery and Uniform Uncertainty Principles SPIE - IE 2008 Deanna Needell Joint work with Roman Vershynin UC Davis, January 2008 Greedy Signal Recovery and Uniform Uncertainty Principles

More information

STAT 200C: High-dimensional Statistics

STAT 200C: High-dimensional Statistics STAT 200C: High-dimensional Statistics Arash A. Amini May 30, 2018 1 / 57 Table of Contents 1 Sparse linear models Basis Pursuit and restricted null space property Sufficient conditions for RNS 2 / 57

More information

arxiv: v2 [cs.it] 8 Apr 2013

arxiv: v2 [cs.it] 8 Apr 2013 ONE-BIT COMPRESSED SENSING WITH NON-GAUSSIAN MEASUREMENTS ALBERT AI, ALEX LAPANOWSKI, YANIV PLAN, AND ROMAN VERSHYNIN arxiv:1208.6279v2 [cs.it] 8 Apr 2013 Abstract. In one-bit compressed sensing, previous

More information

Sparse Fourier Transform (lecture 1)

Sparse Fourier Transform (lecture 1) 1 / 73 Sparse Fourier Transform (lecture 1) Michael Kapralov 1 1 IBM Watson EPFL St. Petersburg CS Club November 2015 2 / 73 Given x C n, compute the Discrete Fourier Transform (DFT) of x: x i = 1 x n

More information

Compressibility of Infinite Sequences and its Interplay with Compressed Sensing Recovery

Compressibility of Infinite Sequences and its Interplay with Compressed Sensing Recovery Compressibility of Infinite Sequences and its Interplay with Compressed Sensing Recovery Jorge F. Silva and Eduardo Pavez Department of Electrical Engineering Information and Decision Systems Group Universidad

More information

Sub-Gaussian Estimators of the Mean of a Random Matrix with Entries Possessing Only Two Moments

Sub-Gaussian Estimators of the Mean of a Random Matrix with Entries Possessing Only Two Moments Sub-Gaussian Estimators of the Mean of a Random Matrix with Entries Possessing Only Two Moments Stas Minsker University of Southern California July 21, 2016 ICERM Workshop Simple question: how to estimate

More information

Information-Theoretic Limits of Group Testing: Phase Transitions, Noisy Tests, and Partial Recovery

Information-Theoretic Limits of Group Testing: Phase Transitions, Noisy Tests, and Partial Recovery Information-Theoretic Limits of Group Testing: Phase Transitions, Noisy Tests, and Partial Recovery Jonathan Scarlett jonathan.scarlett@epfl.ch Laboratory for Information and Inference Systems (LIONS)

More information

Optimal Linear Estimation under Unknown Nonlinear Transform

Optimal Linear Estimation under Unknown Nonlinear Transform Optimal Linear Estimation under Unknown Nonlinear Transform Xinyang Yi The University of Texas at Austin yixy@utexas.edu Constantine Caramanis The University of Texas at Austin constantine@utexas.edu Zhaoran

More information

Lecture Notes 9: Constrained Optimization

Lecture Notes 9: Constrained Optimization Optimization-based data analysis Fall 017 Lecture Notes 9: Constrained Optimization 1 Compressed sensing 1.1 Underdetermined linear inverse problems Linear inverse problems model measurements of the form

More information

The Pros and Cons of Compressive Sensing

The Pros and Cons of Compressive Sensing The Pros and Cons of Compressive Sensing Mark A. Davenport Stanford University Department of Statistics Compressive Sensing Replace samples with general linear measurements measurements sampled signal

More information

CDS 270-2: Lecture 6-1 Towards a Packet-based Control Theory

CDS 270-2: Lecture 6-1 Towards a Packet-based Control Theory Goals: CDS 270-2: Lecture 6-1 Towards a Packet-based Control Theory Ling Shi May 1 2006 - Describe main issues with a packet-based control system - Introduce common models for a packet-based control system

More information

Noisy Signal Recovery via Iterative Reweighted L1-Minimization

Noisy Signal Recovery via Iterative Reweighted L1-Minimization Noisy Signal Recovery via Iterative Reweighted L1-Minimization Deanna Needell UC Davis / Stanford University Asilomar SSC, November 2009 Problem Background Setup 1 Suppose x is an unknown signal in R d.

More information

The Pros and Cons of Compressive Sensing

The Pros and Cons of Compressive Sensing The Pros and Cons of Compressive Sensing Mark A. Davenport Stanford University Department of Statistics Compressive Sensing Replace samples with general linear measurements measurements sampled signal

More information

Reconstruction from Anisotropic Random Measurements

Reconstruction from Anisotropic Random Measurements Reconstruction from Anisotropic Random Measurements Mark Rudelson and Shuheng Zhou The University of Michigan, Ann Arbor Coding, Complexity, and Sparsity Workshop, 013 Ann Arbor, Michigan August 7, 013

More information

Overview. Optimization-Based Data Analysis. Carlos Fernandez-Granda

Overview. Optimization-Based Data Analysis.   Carlos Fernandez-Granda Overview Optimization-Based Data Analysis http://www.cims.nyu.edu/~cfgranda/pages/obda_spring16 Carlos Fernandez-Granda 1/25/2016 Sparsity Denoising Regression Inverse problems Low-rank models Matrix completion

More information

Sparse and Low Rank Recovery via Null Space Properties

Sparse and Low Rank Recovery via Null Space Properties Sparse and Low Rank Recovery via Null Space Properties Holger Rauhut Lehrstuhl C für Mathematik (Analysis), RWTH Aachen Convexity, probability and discrete structures, a geometric viewpoint Marne-la-Vallée,

More information

High-dimensional graphical model selection: Practical and information-theoretic limits

High-dimensional graphical model selection: Practical and information-theoretic limits 1 High-dimensional graphical model selection: Practical and information-theoretic limits Martin Wainwright Departments of Statistics, and EECS UC Berkeley, California, USA Based on joint work with: John

More information

Solving Corrupted Quadratic Equations, Provably

Solving Corrupted Quadratic Equations, Provably Solving Corrupted Quadratic Equations, Provably Yuejie Chi London Workshop on Sparse Signal Processing September 206 Acknowledgement Joint work with Yuanxin Li (OSU), Huishuai Zhuang (Syracuse) and Yingbin

More information

High-dimensional graphical model selection: Practical and information-theoretic limits

High-dimensional graphical model selection: Practical and information-theoretic limits 1 High-dimensional graphical model selection: Practical and information-theoretic limits Martin Wainwright Departments of Statistics, and EECS UC Berkeley, California, USA Based on joint work with: John

More information

Constrained optimization

Constrained optimization Constrained optimization DS-GA 1013 / MATH-GA 2824 Optimization-based Data Analysis http://www.cims.nyu.edu/~cfgranda/pages/obda_fall17/index.html Carlos Fernandez-Granda Compressed sensing Convex constrained

More information

ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis

ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis Lecture 3: Sparse signal recovery: A RIPless analysis of l 1 minimization Yuejie Chi The Ohio State University Page 1 Outline

More information

Compressed Sensing and Robust Recovery of Low Rank Matrices

Compressed Sensing and Robust Recovery of Low Rank Matrices Compressed Sensing and Robust Recovery of Low Rank Matrices M. Fazel, E. Candès, B. Recht, P. Parrilo Electrical Engineering, University of Washington Applied and Computational Mathematics Dept., Caltech

More information

Statistics 300B Winter 2018 Final Exam Due 24 Hours after receiving it

Statistics 300B Winter 2018 Final Exam Due 24 Hours after receiving it Statistics 300B Winter 08 Final Exam Due 4 Hours after receiving it Directions: This test is open book and open internet, but must be done without consulting other students. Any consultation of other students

More information

Introduction to Compressed Sensing

Introduction to Compressed Sensing Introduction to Compressed Sensing Alejandro Parada, Gonzalo Arce University of Delaware August 25, 2016 Motivation: Classical Sampling 1 Motivation: Classical Sampling Issues Some applications Radar Spectral

More information

Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality

Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality Communication Lower Bounds for Statistical Estimation Problems via a Distributed Data Processing Inequality Mark Braverman Ankit Garg Tengyu Ma Huy Nguyen David Woodruff DIMACS Workshop on Big Data through

More information

Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection

Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection Plug-in Measure-Transformed Quasi Likelihood Ratio Test for Random Signal Detection Nir Halay and Koby Todros Dept. of ECE, Ben-Gurion University of the Negev, Beer-Sheva, Israel February 13, 2017 1 /

More information

An Introduction to Sparse Approximation

An Introduction to Sparse Approximation An Introduction to Sparse Approximation Anna C. Gilbert Department of Mathematics University of Michigan Basic image/signal/data compression: transform coding Approximate signals sparsely Compress images,

More information

Model-Based Compressive Sensing for Signal Ensembles. Marco F. Duarte Volkan Cevher Richard G. Baraniuk

Model-Based Compressive Sensing for Signal Ensembles. Marco F. Duarte Volkan Cevher Richard G. Baraniuk Model-Based Compressive Sensing for Signal Ensembles Marco F. Duarte Volkan Cevher Richard G. Baraniuk Concise Signal Structure Sparse signal: only K out of N coordinates nonzero model: union of K-dimensional

More information

IEOR 265 Lecture 3 Sparse Linear Regression

IEOR 265 Lecture 3 Sparse Linear Regression IOR 65 Lecture 3 Sparse Linear Regression 1 M Bound Recall from last lecture that the reason we are interested in complexity measures of sets is because of the following result, which is known as the M

More information

Recent Developments in Compressed Sensing

Recent Developments in Compressed Sensing Recent Developments in Compressed Sensing M. Vidyasagar Distinguished Professor, IIT Hyderabad m.vidyasagar@iith.ac.in, www.iith.ac.in/ m vidyasagar/ ISL Seminar, Stanford University, 19 April 2018 Outline

More information

1 Regression with High Dimensional Data

1 Regression with High Dimensional Data 6.883 Learning with Combinatorial Structure ote for Lecture 11 Instructor: Prof. Stefanie Jegelka Scribe: Xuhong Zhang 1 Regression with High Dimensional Data Consider the following regression problem:

More information

The Stability of Low-Rank Matrix Reconstruction: a Constrained Singular Value Perspective

The Stability of Low-Rank Matrix Reconstruction: a Constrained Singular Value Perspective Forty-Eighth Annual Allerton Conference Allerton House UIUC Illinois USA September 9 - October 1 010 The Stability of Low-Rank Matrix Reconstruction: a Constrained Singular Value Perspective Gongguo Tang

More information

Robust Sparse Recovery via Non-Convex Optimization

Robust Sparse Recovery via Non-Convex Optimization Robust Sparse Recovery via Non-Convex Optimization Laming Chen and Yuantao Gu Department of Electronic Engineering, Tsinghua University Homepage: http://gu.ee.tsinghua.edu.cn/ Email: gyt@tsinghua.edu.cn

More information

Robust Principal Component Analysis

Robust Principal Component Analysis ELE 538B: Mathematics of High-Dimensional Data Robust Principal Component Analysis Yuxin Chen Princeton University, Fall 2018 Disentangling sparse and low-rank matrices Suppose we are given a matrix M

More information

Random hyperplane tessellations and dimension reduction

Random hyperplane tessellations and dimension reduction Random hyperplane tessellations and dimension reduction Roman Vershynin University of Michigan, Department of Mathematics Phenomena in high dimensions in geometric analysis, random matrices and computational

More information

A Majorize-Minimize subspace approach for l 2 -l 0 regularization with applications to image processing

A Majorize-Minimize subspace approach for l 2 -l 0 regularization with applications to image processing A Majorize-Minimize subspace approach for l 2 -l 0 regularization with applications to image processing Emilie Chouzenoux emilie.chouzenoux@univ-mlv.fr Université Paris-Est Lab. d Informatique Gaspard

More information

Supremum of simple stochastic processes

Supremum of simple stochastic processes Subspace embeddings Daniel Hsu COMS 4772 1 Supremum of simple stochastic processes 2 Recap: JL lemma JL lemma. For any ε (0, 1/2), point set S R d of cardinality 16 ln n S = n, and k N such that k, there

More information

ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis

ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis ECE 8201: Low-dimensional Signal Models for High-dimensional Data Analysis Lecture 7: Matrix completion Yuejie Chi The Ohio State University Page 1 Reference Guaranteed Minimum-Rank Solutions of Linear

More information

Combining geometry and combinatorics

Combining geometry and combinatorics Combining geometry and combinatorics A unified approach to sparse signal recovery Anna C. Gilbert University of Michigan joint work with R. Berinde (MIT), P. Indyk (MIT), H. Karloff (AT&T), M. Strauss

More information

Elaine T. Hale, Wotao Yin, Yin Zhang

Elaine T. Hale, Wotao Yin, Yin Zhang , Wotao Yin, Yin Zhang Department of Computational and Applied Mathematics Rice University McMaster University, ICCOPT II-MOPTA 2007 August 13, 2007 1 with Noise 2 3 4 1 with Noise 2 3 4 1 with Noise 2

More information

Equivalence Probability and Sparsity of Two Sparse Solutions in Sparse Representation

Equivalence Probability and Sparsity of Two Sparse Solutions in Sparse Representation IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 19, NO. 12, DECEMBER 2008 2009 Equivalence Probability and Sparsity of Two Sparse Solutions in Sparse Representation Yuanqing Li, Member, IEEE, Andrzej Cichocki,

More information

Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1

Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1 Upper Bound for Intermediate Singular Values of Random Sub-Gaussian Matrices 1 Feng Wei 2 University of Michigan July 29, 2016 1 This presentation is based a project under the supervision of M. Rudelson.

More information

Recent developments on sparse representation

Recent developments on sparse representation Recent developments on sparse representation Zeng Tieyong Department of Mathematics, Hong Kong Baptist University Email: zeng@hkbu.edu.hk Hong Kong Baptist University Dec. 8, 2008 First Previous Next Last

More information

arxiv: v5 [math.na] 16 Nov 2017

arxiv: v5 [math.na] 16 Nov 2017 RANDOM PERTURBATION OF LOW RANK MATRICES: IMPROVING CLASSICAL BOUNDS arxiv:3.657v5 [math.na] 6 Nov 07 SEAN O ROURKE, VAN VU, AND KE WANG Abstract. Matrix perturbation inequalities, such as Weyl s theorem

More information

SCRIBERS: SOROOSH SHAFIEEZADEH-ABADEH, MICHAËL DEFFERRARD

SCRIBERS: SOROOSH SHAFIEEZADEH-ABADEH, MICHAËL DEFFERRARD EE-731: ADVANCED TOPICS IN DATA SCIENCES LABORATORY FOR INFORMATION AND INFERENCE SYSTEMS SPRING 2016 INSTRUCTOR: VOLKAN CEVHER SCRIBERS: SOROOSH SHAFIEEZADEH-ABADEH, MICHAËL DEFFERRARD STRUCTURED SPARSITY

More information

Signal Recovery From Incomplete and Inaccurate Measurements via Regularized Orthogonal Matching Pursuit

Signal Recovery From Incomplete and Inaccurate Measurements via Regularized Orthogonal Matching Pursuit Signal Recovery From Incomplete and Inaccurate Measurements via Regularized Orthogonal Matching Pursuit Deanna Needell and Roman Vershynin Abstract We demonstrate a simple greedy algorithm that can reliably

More information

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation Instructor: Moritz Hardt Email: hardt+ee227c@berkeley.edu Graduate Instructor: Max Simchowitz Email: msimchow+ee227c@berkeley.edu

More information

Acceleration of Randomized Kaczmarz Method

Acceleration of Randomized Kaczmarz Method Acceleration of Randomized Kaczmarz Method Deanna Needell [Joint work with Y. Eldar] Stanford University BIRS Banff, March 2011 Problem Background Setup Setup Let Ax = b be an overdetermined consistent

More information

Sampling and high-dimensional convex geometry

Sampling and high-dimensional convex geometry Sampling and high-dimensional convex geometry Roman Vershynin SampTA 2013 Bremen, Germany, June 2013 Geometry of sampling problems Signals live in high dimensions; sampling is often random. Geometry in

More information

Iterative Projection Methods

Iterative Projection Methods Iterative Projection Methods for noisy and corrupted systems of linear equations Deanna Needell February 1, 2018 Mathematics UCLA joint with Jamie Haddock and Jesús De Loera https://arxiv.org/abs/1605.01418

More information

Recovering overcomplete sparse representations from structured sensing

Recovering overcomplete sparse representations from structured sensing Recovering overcomplete sparse representations from structured sensing Deanna Needell Claremont McKenna College Feb. 2015 Support: Alfred P. Sloan Foundation and NSF CAREER #1348721. Joint work with Felix

More information

Graph Partitioning Using Random Walks

Graph Partitioning Using Random Walks Graph Partitioning Using Random Walks A Convex Optimization Perspective Lorenzo Orecchia Computer Science Why Spectral Algorithms for Graph Problems in practice? Simple to implement Can exploit very efficient

More information

Compressive Sampling for Energy Efficient Event Detection

Compressive Sampling for Energy Efficient Event Detection Compressive Sampling for Energy Efficient Event Detection Zainul Charbiwala, Younghun Kim, Sadaf Zahedi, Jonathan Friedman, and Mani B. Srivastava Physical Signal Sampling Processing Communication Detection

More information

Regularized PCA to denoise and visualise data

Regularized PCA to denoise and visualise data Regularized PCA to denoise and visualise data Marie Verbanck Julie Josse François Husson Laboratoire de statistique, Agrocampus Ouest, Rennes, France CNAM, Paris, 16 janvier 2013 1 / 30 Outline 1 PCA 2

More information

Linear Convergence of Adaptively Iterative Thresholding Algorithms for Compressed Sensing

Linear Convergence of Adaptively Iterative Thresholding Algorithms for Compressed Sensing Linear Convergence of Adaptively Iterative Thresholding Algorithms for Compressed Sensing Yu Wang, Jinshan Zeng, Zhimin Peng, Xiangyu Chang, and Zongben Xu arxiv:48.689v3 [math.oc] 6 Dec 5 Abstract This

More information

MCMC Sampling for Bayesian Inference using L1-type Priors

MCMC Sampling for Bayesian Inference using L1-type Priors MÜNSTER MCMC Sampling for Bayesian Inference using L1-type Priors (what I do whenever the ill-posedness of EEG/MEG is just not frustrating enough!) AG Imaging Seminar Felix Lucka 26.06.2012 , MÜNSTER Sampling

More information

CoSaMP: Greedy Signal Recovery and Uniform Uncertainty Principles

CoSaMP: Greedy Signal Recovery and Uniform Uncertainty Principles CoSaMP: Greedy Signal Recovery and Uniform Uncertainty Principles SIAM Student Research Conference Deanna Needell Joint work with Roman Vershynin and Joel Tropp UC Davis, May 2008 CoSaMP: Greedy Signal

More information

Strengthened Sobolev inequalities for a random subspace of functions

Strengthened Sobolev inequalities for a random subspace of functions Strengthened Sobolev inequalities for a random subspace of functions Rachel Ward University of Texas at Austin April 2013 2 Discrete Sobolev inequalities Proposition (Sobolev inequality for discrete images)

More information

Invertibility of random matrices

Invertibility of random matrices University of Michigan February 2011, Princeton University Origins of Random Matrix Theory Statistics (Wishart matrices) PCA of a multivariate Gaussian distribution. [Gaël Varoquaux s blog gael-varoquaux.info]

More information

Applying Bayesian Estimation to Noisy Simulation Optimization

Applying Bayesian Estimation to Noisy Simulation Optimization Applying Bayesian Estimation to Noisy Simulation Optimization Geng Deng Michael C. Ferris University of Wisconsin-Madison INFORMS Annual Meeting Pittsburgh 2006 Simulation-based optimization problem Computer

More information

An iterative hard thresholding estimator for low rank matrix recovery

An iterative hard thresholding estimator for low rank matrix recovery An iterative hard thresholding estimator for low rank matrix recovery Alexandra Carpentier - based on a joint work with Arlene K.Y. Kim Statistical Laboratory, Department of Pure Mathematics and Mathematical

More information

Resolving the White Noise Paradox in the Regularisation of Inverse Problems

Resolving the White Noise Paradox in the Regularisation of Inverse Problems 1 / 32 Resolving the White Noise Paradox in the Regularisation of Inverse Problems Hanne Kekkonen joint work with Matti Lassas and Samuli Siltanen Department of Mathematics and Statistics University of

More information

ACCORDING to Shannon s sampling theorem, an analog

ACCORDING to Shannon s sampling theorem, an analog 554 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL 59, NO 2, FEBRUARY 2011 Segmented Compressed Sampling for Analog-to-Information Conversion: Method and Performance Analysis Omid Taheri, Student Member,

More information

Corrupted Sensing: Novel Guarantees for Separating Structured Signals

Corrupted Sensing: Novel Guarantees for Separating Structured Signals 1 Corrupted Sensing: Novel Guarantees for Separating Structured Signals Rina Foygel and Lester Mackey Department of Statistics, Stanford University arxiv:130554v csit 4 Feb 014 Abstract We study the problem

More information

Signal Recovery, Uncertainty Relations, and Minkowski Dimension

Signal Recovery, Uncertainty Relations, and Minkowski Dimension Signal Recovery, Uncertainty Relations, and Minkowski Dimension Helmut Bőlcskei ETH Zurich December 2013 Joint work with C. Aubel, P. Kuppinger, G. Pope, E. Riegler, D. Stotz, and C. Studer Aim of this

More information

Lecture 11: Polar codes construction

Lecture 11: Polar codes construction 15-859: Information Theory and Applications in TCS CMU: Spring 2013 Lecturer: Venkatesan Guruswami Lecture 11: Polar codes construction February 26, 2013 Scribe: Dan Stahlke 1 Polar codes: recap of last

More information

Image Processing in Astrophysics

Image Processing in Astrophysics AIM-CEA Saclay, France Image Processing in Astrophysics Sandrine Pires sandrine.pires@cea.fr NDPI 2011 Image Processing : Goals Image processing is used once the image acquisition is done by the telescope

More information

Gauge optimization and duality

Gauge optimization and duality 1 / 54 Gauge optimization and duality Junfeng Yang Department of Mathematics Nanjing University Joint with Shiqian Ma, CUHK September, 2015 2 / 54 Outline Introduction Duality Lagrange duality Fenchel

More information

An algebraic perspective on integer sparse recovery

An algebraic perspective on integer sparse recovery An algebraic perspective on integer sparse recovery Lenny Fukshansky Claremont McKenna College (joint work with Deanna Needell and Benny Sudakov) Combinatorics Seminar USC October 31, 2018 From Wikipedia:

More information

Towards control over fading channels

Towards control over fading channels Towards control over fading channels Paolo Minero, Massimo Franceschetti Advanced Network Science University of California San Diego, CA, USA mail: {minero,massimo}@ucsd.edu Invited Paper) Subhrakanti

More information

arxiv: v2 [cs.lg] 6 May 2017

arxiv: v2 [cs.lg] 6 May 2017 arxiv:170107895v [cslg] 6 May 017 Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity Abstract Adarsh Barik Krannert School of Management Purdue University West Lafayette,

More information

Random Coding for Fast Forward Modeling

Random Coding for Fast Forward Modeling Random Coding for Fast Forward Modeling Justin Romberg with William Mantzel, Salman Asif, Karim Sabra, Ramesh Neelamani Georgia Tech, School of ECE Workshop on Sparsity and Computation June 11, 2010 Bonn,

More information

Sparse Recovery from Inaccurate Saturated Measurements

Sparse Recovery from Inaccurate Saturated Measurements Sparse Recovery from Inaccurate Saturated Measurements Simon Foucart and Jiangyuan Li Texas A&M University Abstract This article studies a variation of the standard compressive sensing problem, in which

More information

Vector Approximate Message Passing. Phil Schniter

Vector Approximate Message Passing. Phil Schniter Vector Approximate Message Passing Phil Schniter Collaborators: Sundeep Rangan (NYU), Alyson Fletcher (UCLA) Supported in part by NSF grant CCF-1527162. itwist @ Aalborg University Aug 24, 2016 Standard

More information

Statistical Inference

Statistical Inference Statistical Inference Classical and Bayesian Methods Class 7 AMS-UCSC Tue 31, 2012 Winter 2012. Session 1 (Class 7) AMS-132/206 Tue 31, 2012 1 / 13 Topics Topics We will talk about... 1 Hypothesis testing

More information

PCA with random noise. Van Ha Vu. Department of Mathematics Yale University

PCA with random noise. Van Ha Vu. Department of Mathematics Yale University PCA with random noise Van Ha Vu Department of Mathematics Yale University An important problem that appears in various areas of applied mathematics (in particular statistics, computer science and numerical

More information

Exponential decay of reconstruction error from binary measurements of sparse signals

Exponential decay of reconstruction error from binary measurements of sparse signals Exponential decay of reconstruction error from binary measurements of sparse signals Deanna Needell Joint work with R. Baraniuk, S. Foucart, Y. Plan, and M. Wootters Outline Introduction Mathematical Formulation

More information

6.842 Randomness and Computation April 2, Lecture 14

6.842 Randomness and Computation April 2, Lecture 14 6.84 Randomness and Computation April, 0 Lecture 4 Lecturer: Ronitt Rubinfeld Scribe: Aaron Sidford Review In the last class we saw an algorithm to learn a function where very little of the Fourier coeffecient

More information

Fast and Robust Phase Retrieval

Fast and Robust Phase Retrieval Fast and Robust Phase Retrieval Aditya Viswanathan aditya@math.msu.edu CCAM Lunch Seminar Purdue University April 18 2014 0 / 27 Joint work with Yang Wang Mark Iwen Research supported in part by National

More information

Performance Analysis for Sparse Support Recovery

Performance Analysis for Sparse Support Recovery Performance Analysis for Sparse Support Recovery Gongguo Tang and Arye Nehorai ESE, Washington University April 21st 2009 Gongguo Tang and Arye Nehorai (Institute) Performance Analysis for Sparse Support

More information

System Identification, Lecture 4

System Identification, Lecture 4 System Identification, Lecture 4 Kristiaan Pelckmans (IT/UU, 2338) Course code: 1RT880, Report code: 61800 - Spring 2012 F, FRI Uppsala University, Information Technology 30 Januari 2012 SI-2012 K. Pelckmans

More information

The PAC Learning Framework -II

The PAC Learning Framework -II The PAC Learning Framework -II Prof. Dan A. Simovici UMB 1 / 1 Outline 1 Finite Hypothesis Space - The Inconsistent Case 2 Deterministic versus stochastic scenario 3 Bayes Error and Noise 2 / 1 Outline

More information

On Acceleration with Noise-Corrupted Gradients. + m k 1 (x). By the definition of Bregman divergence:

On Acceleration with Noise-Corrupted Gradients. + m k 1 (x). By the definition of Bregman divergence: A Omitted Proofs from Section 3 Proof of Lemma 3 Let m x) = a i On Acceleration with Noise-Corrupted Gradients fxi ), u x i D ψ u, x 0 ) denote the function under the minimum in the lower bound By Proposition

More information

System Identification, Lecture 4

System Identification, Lecture 4 System Identification, Lecture 4 Kristiaan Pelckmans (IT/UU, 2338) Course code: 1RT880, Report code: 61800 - Spring 2016 F, FRI Uppsala University, Information Technology 13 April 2016 SI-2016 K. Pelckmans

More information

Random projections. 1 Introduction. 2 Dimensionality reduction. Lecture notes 5 February 29, 2016

Random projections. 1 Introduction. 2 Dimensionality reduction. Lecture notes 5 February 29, 2016 Lecture notes 5 February 9, 016 1 Introduction Random projections Random projections are a useful tool in the analysis and processing of high-dimensional data. We will analyze two applications that use

More information

Stability and robustness of l 1 -minimizations with Weibull matrices and redundant dictionaries

Stability and robustness of l 1 -minimizations with Weibull matrices and redundant dictionaries Stability and robustness of l 1 -minimizations with Weibull matrices and redundant dictionaries Simon Foucart, Drexel University Abstract We investigate the recovery of almost s-sparse vectors x C N from

More information

Binary matrix completion

Binary matrix completion Binary matrix completion Yaniv Plan University of Michigan SAMSI, LDHD workshop, 2013 Joint work with (a) Mark Davenport (b) Ewout van den Berg (c) Mary Wootters Yaniv Plan (U. Mich.) Binary matrix completion

More information

Ergodicity in data assimilation methods

Ergodicity in data assimilation methods Ergodicity in data assimilation methods David Kelly Andy Majda Xin Tong Courant Institute New York University New York NY www.dtbkelly.com April 15, 2016 ETH Zurich David Kelly (CIMS) Data assimilation

More information

Learning Structured Probability Matrices!

Learning Structured Probability Matrices! Learning Structured Probability Matrices Qingqing Huang 2016 February Laboratory for Information & Decision Systems Based on joint work with Sham Kakade, Weihao Kong and Greg Valiant. 1 2 Learning Data

More information

Efficient Variational Inference in Large-Scale Bayesian Compressed Sensing

Efficient Variational Inference in Large-Scale Bayesian Compressed Sensing Efficient Variational Inference in Large-Scale Bayesian Compressed Sensing George Papandreou and Alan Yuille Department of Statistics University of California, Los Angeles ICCV Workshop on Information

More information

Limit theorems for dependent regularly varying functions of Markov chains

Limit theorems for dependent regularly varying functions of Markov chains Limit theorems for functions of with extremal linear behavior Limit theorems for dependent regularly varying functions of In collaboration with T. Mikosch Olivier Wintenberger wintenberger@ceremade.dauphine.fr

More information

Model Selection and Geometry

Model Selection and Geometry Model Selection and Geometry Pascal Massart Université Paris-Sud, Orsay Leipzig, February Purpose of the talk! Concentration of measure plays a fundamental role in the theory of model selection! Model

More information

Multiplicative Perturbation Bounds of the Group Inverse and Oblique Projection

Multiplicative Perturbation Bounds of the Group Inverse and Oblique Projection Filomat 30: 06, 37 375 DOI 0.98/FIL67M Published by Faculty of Sciences Mathematics, University of Niš, Serbia Available at: http://www.pmf.ni.ac.rs/filomat Multiplicative Perturbation Bounds of the Group

More information

Lecture 5 : Projections

Lecture 5 : Projections Lecture 5 : Projections EE227C. Lecturer: Professor Martin Wainwright. Scribe: Alvin Wan Up until now, we have seen convergence rates of unconstrained gradient descent. Now, we consider a constrained minimization

More information

Fast Angular Synchronization for Phase Retrieval via Incomplete Information

Fast Angular Synchronization for Phase Retrieval via Incomplete Information Fast Angular Synchronization for Phase Retrieval via Incomplete Information Aditya Viswanathan a and Mark Iwen b a Department of Mathematics, Michigan State University; b Department of Mathematics & Department

More information

arxiv: v3 [stat.me] 8 Jun 2018

arxiv: v3 [stat.me] 8 Jun 2018 Between hard and soft thresholding: optimal iterative thresholding algorithms Haoyang Liu and Rina Foygel Barber arxiv:804.0884v3 [stat.me] 8 Jun 08 June, 08 Abstract Iterative thresholding algorithms

More information

New ways of dimension reduction? Cutting data sets into small pieces

New ways of dimension reduction? Cutting data sets into small pieces New ways of dimension reduction? Cutting data sets into small pieces Roman Vershynin University of Michigan, Department of Mathematics Statistical Machine Learning Ann Arbor, June 5, 2012 Joint work with

More information