BEYOND MATRIX COMPLETION
|
|
- Rose Hensley
- 5 years ago
- Views:
Transcription
1 BEYOND MATRIX COMPLETION ANKUR MOITRA MASSACHUSETTS INSTITUTE OF TECHNOLOGY Based on joint work with Boaz Barak (MSR)
2 Part I: RecommendaIon systems and parially observed matrices
3 THE NETFLIX PROBLEM movies users
4 THE NETFLIX PROBLEM movies users 1-5 stars
5 THE NETFLIX PROBLEM movies users 480,189 17,770
6 THE NETFLIX PROBLEM movies users 1% observed 480,189 17,770
7 THE NETFLIX PROBLEM movies users 1% observed 480,189 17,770 Can we (approximately) fill- in the missing entries?
8 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix
9 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M + + +
10 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M drama
11 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M drama comedy
12 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M drama comedy sports
13 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M drama comedy sports Model: we are given random observaions M i,j for all i,j Ω
14 MATRIX COMPLETION Let M be an unknown, approximately low- rank matrix M drama comedy sports Model: we are given random observaions M i,j for all i,j Ω Is there an efficient algorithm to recover M?
15 MATRIX COMPLETION The natural formulaion is non- convex, and NP- hard min rank(x) s.t. 1 Ω (i,j) Ω X i,j M i,j η
16 MATRIX COMPLETION The natural formulaion is non- convex, and NP- hard min rank(x) s.t. 1 Ω (i,j) Ω There is a powerful, convex relaxaion X i,j M i,j η
17 THE NUCLEAR NORM Consider the singular value decomposi;on of X: X = U Σ V T orthogonal diagonal orthogonal
18 THE NUCLEAR NORM Consider the singular value decomposi;on of X: X = U Σ V T orthogonal diagonal orthogonal Let σ 1 σ 2 σ r > σ r+1 = σ m = 0 be the singular values
19 THE NUCLEAR NORM Consider the singular value decomposi;on of X: X = U Σ V T orthogonal diagonal orthogonal Let σ 1 σ 2 σ r > σ r+1 = σ m = 0 be the singular values Then rank(x) = r, and X * = σ 1 + σ σ r (nuclear norm)
20 This yields a convex relaxaion, that can be solved efficiently: min X * s.t. 1 Ω (i,j) Ω X i,j M i,j η [Fazel], [Srebro, Shraibman], [Recht, Fazel, Parrilo], [Candes, Recht], [Candes, Tao], [Candes, Plan], [Recht], (P)
21 This yields a convex relaxaion, that can be solved efficiently: min X * s.t. 1 Ω (i,j) Ω X i,j M i,j η [Fazel], [Srebro, Shraibman], [Recht, Fazel, Parrilo], [Candes, Recht], [Candes, Tao], [Candes, Plan], [Recht], (P) Theorem: If M is n x n and has rank r, and is C- incoherent then (P) recovers M exactly from C 6 nrlog 2 n observaions
22 This yields a convex relaxaion, that can be solved efficiently: min X * s.t. 1 Ω (i,j) Ω X i,j M i,j η [Fazel], [Srebro, Shraibman], [Recht, Fazel, Parrilo], [Candes, Recht], [Candes, Tao], [Candes, Plan], [Recht], (P) Theorem: If M is n x n and has rank r, and is C- incoherent then (P) recovers M exactly from C 6 nrlog 2 n observaions This is nearly opimal, since there are 2nr parameters
23 This yields a convex relaxaion, that can be solved efficiently: min X * s.t. 1 Ω (i,j) Ω X i,j M i,j η [Fazel], [Srebro, Shraibman], [Recht, Fazel, Parrilo], [Candes, Recht], [Candes, Tao], [Candes, Plan], [Recht], (P) Theorem: If M is n x n and has rank r, and is C- incoherent then (P) recovers M exactly from C 6 nrlog 2 n observaions This is nearly opimal, since there are 2nr parameters Many other approaches, e.g. alterna;ng minimiza;on: [Keshavan, Montanari, Oh], [Jain, Netrapalli, Sanghavi], [Hardt],
24 Part II: Higher order structure?
25 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions?
26 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? ac;vi;es users e.g. Groupon
27 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? ;me users e.g. Groupon ;me: season, Ime of day, weekday/weekend, etc
28 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? users ;me T = r i = 1 e.g. Groupon snow sports ;me: season, Ime of day, weekday/weekend, etc
29 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? users ;me r T = a i b i c i i = 1
30 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? users ;me r T = a i b i c i i = 1 Can we (approximately) fill- in the missing entries?
31 TENSOR PREDICTION Can using more than two asributes can lead to beser recommendaions? users ;me r T = a i b i c i i = 1 Can we (approximately) fill- in the missing entries? More asributes lead to beser recommendaions, but more complex objects
32 THE TROUBLE WITH TENSORS Natural approach (suggested by many authors): min X s.t. * 1 Ω (i,j,k) Ω X i,j,k T i,j,k η (P) tensor nuclear norm
33 THE TROUBLE WITH TENSORS Natural approach (suggested by many authors): min X s.t. * 1 Ω (i,j,k) Ω X i,j,k T i,j,k η (P) tensor nuclear norm The tensor nuclear norm is NP- hard to compute! [Gurvits], [Liu], [Harrow, Montanaro]
34 In fact, most of the linear algebra toolkit is ill- posed, or computa;onally hard for tensors
35 In fact, most of the linear algebra toolkit is ill- posed, or computa;onally hard for tensors e.g. [Hillar, Lim] Most Tensor Problems are NP- Hard
36 In fact, most of the linear algebra toolkit is ill- posed, or computa;onally hard for tensors e.g. [Hillar, Lim] Most Tensor Problems are NP- Hard Table I. Tractability of Tensor Problems Problem Complexity Bivariate Matrix Functions over R, C Undecidable (Proposition 12.2) Bilinear System over R, C NP-hard (Theorems 2.6, 3.7, 3.8) Eigenvalue over R NP-hard (Theorem 1.3) Approximating Eigenvector over R NP-hard (Theorem 1.5) Symmetric Eigenvalue over R NP-hard (Theorem 9.3) Approximating Symmetric Eigenvalue over R NP-hard (Theorem 9.6) Singular Value over R, C NP-hard (Theorem 1.7) Symmetric Singular Value over R NP-hard (Theorem 10.2) Approximating Singular Vector over R, C NP-hard (Theorem 6.3) Spectral Norm over R NP-hard (Theorem 1.10) Symmetric Spectral Norm over R NP-hard (Theorem 10.2) Approximating Spectral Norm over R NP-hard (Theorem 1.11) Nonnegative Definiteness NP-hard (Theorem 11.2) Best Rank-1 Approximation NP-hard (Theorem 1.13) Best Symmetric Rank-1 Approximation NP-hard (Theorem 10.2) Rank over R or C NP-hard (Theorem 8.2) Enumerating Eigenvectors over R #P-hard (Corollary 1.16) Combinatorial Hyperdeterminant NP-, #P-, VNP-hard (Theorems 4.1, 4.2, Corollary 4.3) Geometric Hyperdeterminant Conjectures 1.9, 13.1 Symmetric Rank Conjecture 13.2 Bilinear Programming Conjecture 13.4 Bilinear Least Squares Conjecture 13.5 Note: Except for positive definiteness and the combinatorial hyperdeterminant, which apply to -tensors,
37 FLATTENING A TENSOR Many tensor methods rely on flatening:
38 FLATTENING A TENSOR Many tensor methods rely on flatening: n 3 flat( ) = n 1 n 1 n 2 n 3
39 FLATTENING A TENSOR Many tensor methods rely on flatening: n 3 flat( ) = n 1 users ac;vi;es ;me
40 FLATTENING A TENSOR Many tensor methods rely on flatening: flat( ) = n 1 n 3 i (j,k) T i,j,k
41 FLATTENING A TENSOR Many tensor methods rely on flatening: flat( ) = n 1 n 3 i (j,k) T i,j,k This is a rearrangement of the entries, into a matrix, that does not increase its rank
42 FLATTENING A TENSOR Many tensor methods rely on flatening: flat( ) = n 1 n 3 i r flat( a i b i c i i = 1 r (j,k) ) = a i T vec(b i c i ) i = 1 T i,j,k n 2 n 3 - dimensional vector
43 Let n 1 = n 2 = n 3 = n We would need O(n 2 r) observaions to fill- in flat(t)
44 Let n 1 = n 2 = n 3 = n We would need O(n 2 r) observaions to fill- in flat(t) There are many other variants of flatening, but with comparable guarantees [Liu, Musialski, Wonka, Ye], [Gandy, Recht, Yamada], [SignoreTo, De Lathauwer, Suykens], [Tomioko, Hayashi, Kashima], [Mu, Huang, Wright, Goldfarb],
45 Let n 1 = n 2 = n 3 = n We would need O(n 2 r) observaions to fill- in flat(t) There are many other variants of flatening, but with comparable guarantees [Liu, Musialski, Wonka, Ye], [Gandy, Recht, Yamada], [SignoreTo, De Lathauwer, Suykens], [Tomioko, Hayashi, Kashima], [Mu, Huang, Wright, Goldfarb], Can we beat flasening?
46 Let n 1 = n 2 = n 3 = n We would need O(n 2 r) observaions to fill- in flat(t) There are many other variants of flatening, but with comparable guarantees [Liu, Musialski, Wonka, Ye], [Gandy, Recht, Yamada], [SignoreTo, De Lathauwer, Suykens], [Tomioko, Hayashi, Kashima], [Mu, Huang, Wright, Goldfarb], Can we beat flasening? Can we make beser predicions than we do by treaing each ac;vity x ;me as unrelated?
47 Part III: Nearly opimal algorithms for tensor predicion
48 OUR RESULTS r T = a i b i c i i = 1 σ i + noise standard Gaussian r.v.
49 OUR RESULTS r T = a i b i c i i = 1 σ i + noise standard Gaussian r.v. Theorem: Suppose var(t i,j,k ) r/n 3 polylog(n). Then there is an efficient algorithm that X which saisfies: X i,j,k = (1±o(1))T i,j,k for a 1- o(1) fracion of entries, provided m = Ω (n 3/2 r)
50 OUR RESULTS r T = a i b i c i i = 1 σ i + noise standard Gaussian r.v. Theorem: Suppose var(t i,j,k ) r/n 3 polylog(n). Then there is an efficient algorithm that X which saisfies: X i,j,k = (1±o(1))T i,j,k for a 1- o(1) fracion of entries, provided m = Ω (n 3/2 r) This variance bound holds for random tensors, but also tensors where the factors (a i s, b i s, c i s) have large inner- product
51 OUR RESULTS r T = a i b i c i i = 1 σ i + noise standard Gaussian r.v. Theorem: Suppose var(t i,j,k ) r/n 3 polylog(n). Then there is an efficient algorithm that X which saisfies: X i,j,k = (1±o(1))T i,j,k for a 1- o(1) fracion of entries, provided m = Ω (n 3/2 r) Even for r = n 3/2- δ (highly overcomplete), we only need to observe an o(1) fracion of the entries to predict almost everything
52 LOWER BOUNDS Not only is the tensor nuclear norm hard to compute, but
53 LOWER BOUNDS Not only is the tensor nuclear norm hard to compute, but Tensor predicion with m observaions Refute random 3- SAT with m clauses
54 LOWER BOUNDS Not only is the tensor nuclear norm hard to compute, but Tensor predicion with m observaions Refute random 3- SAT with m clauses The best known algorithms require m = n 3/2, and even powerful SDP hierarchies fail with fewer clauses [Shor], [Nesterov], [Parrilo], [Lasserre], [Grigoriev], [Schoenebeck]
55 LOWER BOUNDS Not only is the tensor nuclear norm hard to compute, but Tensor predicion with m observaions Refute random 3- SAT with m clauses The best known algorithms require m = n 3/2, and even powerful SDP hierarchies fail with fewer clauses [Shor], [Nesterov], [Parrilo], [Lasserre], [Grigoriev], [Schoenebeck] Corollary [informal]: Any algorithm for solving tensor predicion, in the sum- of- squares hierarchy that uses m=n 3/2- δ r observaions must run in exponenial Ime
56 Part IV: Our techniques: connecions to random CSPs
57 Can we disinguish between low- rank and random?
58 Can we disinguish between low- rank and random? Case #1: Approximately low- rank a T a + noise
59 Can we disinguish between low- rank and random? Case #1: Approximately low- rank a T a + noise For each (i,j) Ω M i,j = a i a j w/ probability ¾ random ±1 w/ probability ¼ where each a i = ±1
60 Can we disinguish between low- rank and random?
61 Can we disinguish between low- rank and random? Case #2: Random random For each (i,j) Ω, M i,j = random ±1
62 Can we disinguish between low- rank and random? Case #2: Random random For each (i,j) Ω, M i,j = random ±1 In Case #1 the entries are (somewhat) predictable, but in Case #2 they are completely unpredictable
63 There are two very different communiies that (essenially) asacked this same disinguishing problem:
64 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on
65 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on The community working on refu;ng random CSPs
66 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on The community working on refu;ng random CSPs Matrix predicion with m observaions Strongly refute* random 2- XOR with m clauses *Want an algorithm that cerifies a formula is far from saisfiable
67 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on The community working on refu;ng random CSPs Tensor predic;on with m observaions Strongly refute* random 3- XOR with m clauses *Want an algorithm that cerifies a formula is far from saisfiable
68 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on The community working on refu;ng random CSPs Tensor predic;on with m observaions Strongly refute* random 3- XOR with m clauses [Coja- Oghlan, Goerdt, Lanka] *Want an algorithm that cerifies a formula is far from saisfiable
69 There are two very different communiies that (essenially) asacked this same disinguishing problem: The community working on matrix comple;on The community working on refu;ng random CSPs Tensor predic;on with m observaions Rademacher Complexity Strongly refute* random 3- XOR with m clauses [Coja- Oghlan, Goerdt, Lanka] We then embed this algorithm into the sixth level of the sum- of- squares hierarchy, to get a relaxaion for tensor predicion *Want an algorithm that cerifies a formula is far from saisfiable
70 SUMMARY New Algorithm: We gave an algorithm for 3 rd - order tensor predicion that uses m = n 3/2 rlog 4 n observaions
71 SUMMARY New Algorithm: We gave an algorithm for 3 rd - order tensor predicion that uses m = n 3/2 rlog 4 n observaions An Inefficient Algorithm: (via tensor nuclear norm) There is an inefficient algorithm that use m = nrlogn observaions
72 SUMMARY New Algorithm: We gave an algorithm for 3 rd - order tensor predicion that uses m = n 3/2 rlog 4 n observaions An Inefficient Algorithm: (via tensor nuclear norm) There is an inefficient algorithm that use m = nrlogn observaions A Phase Transi;on: Even for n δ rounds of the powerful sum- of- squares hierarchy, no norm solves tensor predicion with m = n 3/2- δ r observaions
73 DISCUSSION Convex programs are unreasonably effecive for linear inverse problems!
74 DISCUSSION Convex programs are unreasonably effecive for linear inverse problems! But we gave simple linear inverse problems that exhibit striking gaps between efficient and inefficient esimators
75 DISCUSSION Convex programs are unreasonably effecive for linear inverse problems! But we gave simple linear inverse problems that exhibit striking gaps between efficient and inefficient esimators Where else are there computaional vs staisical tradeoffs?
76 DISCUSSION Convex programs are unreasonably effecive for linear inverse problems! But we gave simple linear inverse problems that exhibit striking gaps between efficient and inefficient esimators Where else are there computaional vs staisical tradeoffs? New Direc;on: Explore computaional vs. staisical tradeoffs through the powerful sum- of- squares hierarchy
BEYOND MATRIX COMPLETION
BEYOND MATRIX COMPLETION ANKUR MOITRA MASSACHUSETTS INSTITUTE OF TECHNOLOGY Based on joint work with Boaz Barak (Harvard) Part I: RecommendaJon systems and parjally observed matrices THE NETFLIX PROBLEM
More informationThe convex algebraic geometry of rank minimization
The convex algebraic geometry of rank minimization Pablo A. Parrilo Laboratory for Information and Decision Systems Massachusetts Institute of Technology International Symposium on Mathematical Programming
More informationLinear dimensionality reduction for data analysis
Linear dimensionality reduction for data analysis Nicolas Gillis Joint work with Robert Luce, François Glineur, Stephen Vavasis, Robert Plemmons, Gabriella Casalino The setup Dimensionality reduction for
More informationStatistical Performance of Convex Tensor Decomposition
Slides available: h-p://www.ibis.t.u tokyo.ac.jp/ryotat/tensor12kyoto.pdf Statistical Performance of Convex Tensor Decomposition Ryota Tomioka 2012/01/26 @ Kyoto University Perspectives in Informatics
More informationECE 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 informationRecovering any low-rank matrix, provably
Recovering any low-rank matrix, provably Rachel Ward University of Texas at Austin October, 2014 Joint work with Yudong Chen (U.C. Berkeley), Srinadh Bhojanapalli and Sujay Sanghavi (U.T. Austin) Matrix
More informationMatrix Completion from Fewer Entries
from Fewer Entries Stanford University March 30, 2009 Outline The problem, a look at the data, and some results (slides) 2 Proofs (blackboard) arxiv:090.350 The problem, a look at the data, and some results
More informationCSC 576: Variants of Sparse Learning
CSC 576: Variants of Sparse Learning Ji Liu Department of Computer Science, University of Rochester October 27, 205 Introduction Our previous note basically suggests using l norm to enforce sparsity in
More informationMatrix Completion: Fundamental Limits and Efficient Algorithms
Matrix Completion: Fundamental Limits and Efficient Algorithms Sewoong Oh PhD Defense Stanford University July 23, 2010 1 / 33 Matrix completion Find the missing entries in a huge data matrix 2 / 33 Example
More informationProvable Alternating Minimization Methods for Non-convex Optimization
Provable Alternating Minimization Methods for Non-convex Optimization Prateek Jain Microsoft Research, India Joint work with Praneeth Netrapalli, Sujay Sanghavi, Alekh Agarwal, Animashree Anandkumar, Rashish
More informationRobust 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 informationTensor Low-Rank Completion and Invariance of the Tucker Core
Tensor Low-Rank Completion and Invariance of the Tucker Core Shuzhong Zhang Department of Industrial & Systems Engineering University of Minnesota zhangs@umn.edu Joint work with Bo JIANG, Shiqian MA, and
More informationLow-rank Matrix Completion from Noisy Entries
Low-rank Matrix Completion from Noisy Entries Sewoong Oh Joint work with Raghunandan Keshavan and Andrea Montanari Stanford University Forty-Seventh Allerton Conference October 1, 2009 R.Keshavan, S.Oh,
More informationSum-of-Squares Method, Tensor Decomposition, Dictionary Learning
Sum-of-Squares Method, Tensor Decomposition, Dictionary Learning David Steurer Cornell Approximation Algorithms and Hardness, Banff, August 2014 for many problems (e.g., all UG-hard ones): better guarantees
More informationMatrix completion: Fundamental limits and efficient algorithms. Sewoong Oh Stanford University
Matrix completion: Fundamental limits and efficient algorithms Sewoong Oh Stanford University 1 / 35 Low-rank matrix completion Low-rank Data Matrix Sparse Sampled Matrix Complete the matrix from small
More informationAn Extended Frank-Wolfe Method, with Application to Low-Rank Matrix Completion
An Extended Frank-Wolfe Method, with Application to Low-Rank Matrix Completion Robert M. Freund, MIT joint with Paul Grigas (UC Berkeley) and Rahul Mazumder (MIT) CDC, December 2016 1 Outline of Topics
More informationMATRIX COMPLETION AND TENSOR RANK
MATRIX COMPLETION AND TENSOR RANK HARM DERKSEN Abstract. In this paper, we show that the low rank matrix completion problem can be reduced to the problem of finding the rank of a certain tensor. arxiv:1302.2639v2
More informationLow-rank Matrix Completion with Noisy Observations: a Quantitative Comparison
Low-rank Matrix Completion with Noisy Observations: a Quantitative Comparison Raghunandan H. Keshavan, Andrea Montanari and Sewoong Oh Electrical Engineering and Statistics Department Stanford University,
More informationapproximation algorithms I
SUM-OF-SQUARES method and approximation algorithms I David Steurer Cornell Cargese Workshop, 201 meta-task encoded as low-degree polynomial in R x example: f(x) = i,j n w ij x i x j 2 given: functions
More informationLower bounds on the size of semidefinite relaxations. David Steurer Cornell
Lower bounds on the size of semidefinite relaxations David Steurer Cornell James R. Lee Washington Prasad Raghavendra Berkeley Institute for Advanced Study, November 2015 overview of results unconditional
More informationStructured matrix factorizations. Example: Eigenfaces
Structured matrix factorizations Example: Eigenfaces An extremely large variety of interesting and important problems in machine learning can be formulated as: Given a matrix, find a matrix and a matrix
More informationFrom Compressed Sensing to Matrix Completion and Beyond. Benjamin Recht Department of Computer Sciences University of Wisconsin-Madison
From Compressed Sensing to Matrix Completion and Beyond Benjamin Recht Department of Computer Sciences University of Wisconsin-Madison Netflix Prize One million big ones! Given 100 million ratings on a
More informationMost tensor problems are NP hard
Most tensor problems are NP hard (preliminary report) Lek-Heng Lim University of California, Berkeley August 25, 2009 (Joint work with: Chris Hillar, MSRI) L.H. Lim (Berkeley) Most tensor problems are
More informationRank Determination for Low-Rank Data Completion
Journal of Machine Learning Research 18 017) 1-9 Submitted 7/17; Revised 8/17; Published 9/17 Rank Determination for Low-Rank Data Completion Morteza Ashraphijuo Columbia University New York, NY 1007,
More informationLow Rank Matrix Completion Formulation and Algorithm
1 2 Low Rank Matrix Completion and Algorithm Jian Zhang Department of Computer Science, ETH Zurich zhangjianthu@gmail.com March 25, 2014 Movie Rating 1 2 Critic A 5 5 Critic B 6 5 Jian 9 8 Kind Guy B 9
More informationUnique Games Conjecture & Polynomial Optimization. David Steurer
Unique Games Conjecture & Polynomial Optimization David Steurer Newton Institute, Cambridge, July 2013 overview Proof Complexity Approximability Polynomial Optimization Quantum Information computational
More informationLow-Rank Matrix Recovery
ELE 538B: Mathematics of High-Dimensional Data Low-Rank Matrix Recovery Yuxin Chen Princeton University, Fall 2018 Outline Motivation Problem setup Nuclear norm minimization RIP and low-rank matrix recovery
More informationMulti-stage convex relaxation approach for low-rank structured PSD matrix recovery
Multi-stage convex relaxation approach for low-rank structured PSD matrix recovery Department of Mathematics & Risk Management Institute National University of Singapore (Based on a joint work with Shujun
More informationRank minimization via the γ 2 norm
Rank minimization via the γ 2 norm Troy Lee Columbia University Adi Shraibman Weizmann Institute Rank Minimization Problem Consider the following problem min X rank(x) A i, X b i for i = 1,..., k Arises
More informationSparse and Low-Rank Matrix Decompositions
Forty-Seventh Annual Allerton Conference Allerton House, UIUC, Illinois, USA September 30 - October 2, 2009 Sparse and Low-Rank Matrix Decompositions Venkat Chandrasekaran, Sujay Sanghavi, Pablo A. Parrilo,
More informationBinary 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 informationECE G: Special Topics in Signal Processing: Sparsity, Structure, and Inference
ECE 18-898G: Special Topics in Signal Processing: Sparsity, Structure, and Inference Low-rank matrix recovery via convex relaxations Yuejie Chi Department of Electrical and Computer Engineering Spring
More informationApproximation & Complexity
Summer school on semidefinite optimization Approximation & Complexity David Steurer Cornell University Part 1 September 6, 2012 Overview Part 1 Unique Games Conjecture & Basic SDP Part 2 SDP Hierarchies:
More informationCollaborative Filtering
Case Study 4: Collaborative Filtering Collaborative Filtering Matrix Completion Alternating Least Squares Machine Learning/Statistics for Big Data CSE599C1/STAT592, University of Washington Carlos Guestrin
More informationAdaptive one-bit matrix completion
Adaptive one-bit matrix completion Joseph Salmon Télécom Paristech, Institut Mines-Télécom Joint work with Jean Lafond (Télécom Paristech) Olga Klopp (Crest / MODAL X, Université Paris Ouest) Éric Moulines
More informationCollaborative Filtering Matrix Completion Alternating Least Squares
Case Study 4: Collaborative Filtering Collaborative Filtering Matrix Completion Alternating Least Squares Machine Learning for Big Data CSE547/STAT548, University of Washington Sham Kakade May 19, 2016
More informationarxiv: v1 [math.oc] 11 Jun 2009
RANK-SPARSITY INCOHERENCE FOR MATRIX DECOMPOSITION VENKAT CHANDRASEKARAN, SUJAY SANGHAVI, PABLO A. PARRILO, S. WILLSKY AND ALAN arxiv:0906.2220v1 [math.oc] 11 Jun 2009 Abstract. Suppose we are given a
More informationMINI-TUTORIAL ON SEMI-ALGEBRAIC PROOF SYSTEMS. Albert Atserias Universitat Politècnica de Catalunya Barcelona
MINI-TUTORIAL ON SEMI-ALGEBRAIC PROOF SYSTEMS Albert Atserias Universitat Politècnica de Catalunya Barcelona Part I CONVEX POLYTOPES Convex polytopes as linear inequalities Polytope: P = {x R n : Ax b}
More informationNew Ranks for Even-Order Tensors and Their Applications in Low-Rank Tensor Optimization
New Ranks for Even-Order Tensors and Their Applications in Low-Rank Tensor Optimization Bo JIANG Shiqian MA Shuzhong ZHANG January 12, 2015 Abstract In this paper, we propose three new tensor decompositions
More informationECE 598: Representation Learning: Algorithms and Models Fall 2017
ECE 598: Representation Learning: Algorithms and Models Fall 2017 Lecture 1: Tensor Methods in Machine Learning Lecturer: Pramod Viswanathan Scribe: Bharath V Raghavan, Oct 3, 2017 11 Introduction Tensors
More informationConvex sets, conic matrix factorizations and conic rank lower bounds
Convex sets, conic matrix factorizations and conic rank lower bounds Pablo A. Parrilo Laboratory for Information and Decision Systems Electrical Engineering and Computer Science Massachusetts Institute
More informationECE G: Special Topics in Signal Processing: Sparsity, Structure, and Inference
ECE 18-898G: Special Topics in Signal Processing: Sparsity, Structure, and Inference Low-rank matrix recovery via nonconvex optimization Yuejie Chi Department of Electrical and Computer Engineering Spring
More informationGuaranteed Rank Minimization via Singular Value Projection
3 4 5 6 7 8 9 3 4 5 6 7 8 9 3 4 5 6 7 8 9 3 3 3 33 34 35 36 37 38 39 4 4 4 43 44 45 46 47 48 49 5 5 5 53 Guaranteed Rank Minimization via Singular Value Projection Anonymous Author(s) Affiliation Address
More informationTensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization Canyi Lu 1, Jiashi Feng 1, Yudong Chen, Wei Liu 3, Zhouchen Lin 4,5,, Shuicheng Yan 6,1
More informationA Characterization of Sampling Patterns for Union of Low-Rank Subspaces Retrieval Problem
A Characterization of Sampling Patterns for Union of Low-Rank Subspaces Retrieval Problem Morteza Ashraphijuo Columbia University ashraphijuo@ee.columbia.edu Xiaodong Wang Columbia University wangx@ee.columbia.edu
More informationNon-convex Robust PCA: Provable Bounds
Non-convex Robust PCA: Provable Bounds Anima Anandkumar U.C. Irvine Joint work with Praneeth Netrapalli, U.N. Niranjan, Prateek Jain and Sujay Sanghavi. Learning with Big Data High Dimensional Regime Missing
More informationSemidefinite Programming
Semidefinite Programming Notes by Bernd Sturmfels for the lecture on June 26, 208, in the IMPRS Ringvorlesung Introduction to Nonlinear Algebra The transition from linear algebra to nonlinear algebra has
More informationAnalysis of Robust PCA via Local Incoherence
Analysis of Robust PCA via Local Incoherence Huishuai Zhang Department of EECS Syracuse University Syracuse, NY 3244 hzhan23@syr.edu Yi Zhou Department of EECS Syracuse University Syracuse, NY 3244 yzhou35@syr.edu
More informationarxiv: v1 [stat.ml] 1 Mar 2015
Matrix Completion with Noisy Entries and Outliers Raymond K. W. Wong 1 and Thomas C. M. Lee 2 arxiv:1503.00214v1 [stat.ml] 1 Mar 2015 1 Department of Statistics, Iowa State University 2 Department of Statistics,
More informationInformation-Theoretic Limits of Matrix Completion
Information-Theoretic Limits of Matrix Completion Erwin Riegler, David Stotz, and Helmut Bölcskei Dept. IT & EE, ETH Zurich, Switzerland Email: {eriegler, dstotz, boelcskei}@nari.ee.ethz.ch Abstract We
More informationRapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization
Rapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization Shuyang Ling Department of Mathematics, UC Davis Oct.18th, 2016 Shuyang Ling (UC Davis) 16w5136, Oaxaca, Mexico Oct.18th, 2016
More informationCourse 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 informationApproximate Low-Rank Tensor Learning
Approximate Low-Rank Tensor Learning Yaoliang Yu Dept of Machine Learning Carnegie Mellon University yaoliang@cs.cmu.edu Hao Cheng Dept of Electric Engineering University of Washington kelvinwsch@gmail.com
More information1 Inner Product and Orthogonality
CSCI 4/Fall 6/Vora/GWU/Orthogonality and Norms Inner Product and Orthogonality Definition : The inner product of two vectors x and y, x x x =.., y =. x n y y... y n is denoted x, y : Note that n x, y =
More informationConditions for Robust Principal Component Analysis
Rose-Hulman Undergraduate Mathematics Journal Volume 12 Issue 2 Article 9 Conditions for Robust Principal Component Analysis Michael Hornstein Stanford University, mdhornstein@gmail.com Follow this and
More informationarxiv: 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 informationSpectral k-support Norm Regularization
Spectral k-support Norm Regularization Andrew McDonald Department of Computer Science, UCL (Joint work with Massimiliano Pontil and Dimitris Stamos) 25 March, 2015 1 / 19 Problem: Matrix Completion Goal:
More informationSparse 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 informationOptimization. Benjamin Recht University of California, Berkeley Stephen Wright University of Wisconsin-Madison
Optimization Benjamin Recht University of California, Berkeley Stephen Wright University of Wisconsin-Madison optimization () cost constraints might be too much to cover in 3 hours optimization (for big
More informationTutorial: PART 2. Optimization for Machine Learning. Elad Hazan Princeton University. + help from Sanjeev Arora & Yoram Singer
Tutorial: PART 2 Optimization for Machine Learning Elad Hazan Princeton University + help from Sanjeev Arora & Yoram Singer Agenda 1. Learning as mathematical optimization Stochastic optimization, ERM,
More informationSum-of-Squares and Spectral Algorithms
Sum-of-Squares and Spectral Algorithms Tselil Schramm June 23, 2017 Workshop on SoS @ STOC 2017 Spectral algorithms as a tool for analyzing SoS. SoS Semidefinite Programs Spectral Algorithms SoS suggests
More informationCombining Sparsity with Physically-Meaningful Constraints in Sparse Parameter Estimation
UIUC CSL Mar. 24 Combining Sparsity with Physically-Meaningful Constraints in Sparse Parameter Estimation Yuejie Chi Department of ECE and BMI Ohio State University Joint work with Yuxin Chen (Stanford).
More informationLecture Notes 10: Matrix Factorization
Optimization-based data analysis Fall 207 Lecture Notes 0: Matrix Factorization Low-rank models. Rank- model Consider the problem of modeling a quantity y[i, j] that depends on two indices i and j. To
More informationMatrix Factorizations: A Tale of Two Norms
Matrix Factorizations: A Tale of Two Norms Nati Srebro Toyota Technological Institute Chicago Maximum Margin Matrix Factorization S, Jason Rennie, Tommi Jaakkola (MIT), NIPS 2004 Rank, Trace-Norm and Max-Norm
More informationExact Low-rank Matrix Recovery via Nonconvex M p -Minimization
Exact Low-rank Matrix Recovery via Nonconvex M p -Minimization Lingchen Kong and Naihua Xiu Department of Applied Mathematics, Beijing Jiaotong University, Beijing, 100044, People s Republic of China E-mail:
More informationMatrix Completion from a Few Entries
Matrix Completion from a Few Entries Raghunandan H. Keshavan and Sewoong Oh EE Department Stanford University, Stanford, CA 9434 Andrea Montanari EE and Statistics Departments Stanford University, Stanford,
More informationTHE PERTURBATION BOUND FOR THE SPECTRAL RADIUS OF A NON-NEGATIVE TENSOR
THE PERTURBATION BOUND FOR THE SPECTRAL RADIUS OF A NON-NEGATIVE TENSOR WEN LI AND MICHAEL K. NG Abstract. In this paper, we study the perturbation bound for the spectral radius of an m th - order n-dimensional
More informationBreaking the Limits of Subspace Inference
Breaking the Limits of Subspace Inference Claudia R. Solís-Lemus, Daniel L. Pimentel-Alarcón Emory University, Georgia State University Abstract Inferring low-dimensional subspaces that describe high-dimensional,
More informationCompressive Sensing and Beyond
Compressive Sensing and Beyond Sohail Bahmani Gerorgia Tech. Signal Processing Compressed Sensing Signal Models Classics: bandlimited The Sampling Theorem Any signal with bandwidth B can be recovered
More informationRecovery of Low-Rank Plus Compressed Sparse Matrices with Application to Unveiling Traffic Anomalies
July 12, 212 Recovery of Low-Rank Plus Compressed Sparse Matrices with Application to Unveiling Traffic Anomalies Morteza Mardani Dept. of ECE, University of Minnesota, Minneapolis, MN 55455 Acknowledgments:
More informationSymmetric Factorization for Nonconvex Optimization
Symmetric Factorization for Nonconvex Optimization Qinqing Zheng February 24, 2017 1 Overview A growing body of recent research is shedding new light on the role of nonconvex optimization for tackling
More informationSparsity Models. Tong Zhang. Rutgers University. T. Zhang (Rutgers) Sparsity Models 1 / 28
Sparsity Models Tong Zhang Rutgers University T. Zhang (Rutgers) Sparsity Models 1 / 28 Topics Standard sparse regression model algorithms: convex relaxation and greedy algorithm sparse recovery analysis:
More informationHigh-dimensional Statistics
High-dimensional Statistics Pradeep Ravikumar UT Austin Outline 1. High Dimensional Data : Large p, small n 2. Sparsity 3. Group Sparsity 4. Low Rank 1 Curse of Dimensionality Statistical Learning: Given
More informationUniversal low-rank matrix recovery from Pauli measurements
Universal low-rank matrix recovery from Pauli measurements Yi-Kai Liu Applied and Computational Mathematics Division National Institute of Standards and Technology Gaithersburg, MD, USA yi-kai.liu@nist.gov
More informationConcentration-Based Guarantees for Low-Rank Matrix Reconstruction
JMLR: Workshop and Conference Proceedings 9 20 35 339 24th Annual Conference on Learning Theory Concentration-Based Guarantees for Low-Rank Matrix Reconstruction Rina Foygel Department of Statistics, University
More informationEstimation of (near) low-rank matrices with noise and high-dimensional scaling
Estimation of (near) low-rank matrices with noise and high-dimensional scaling Sahand Negahban Department of EECS, University of California, Berkeley, CA 94720, USA sahand n@eecs.berkeley.edu Martin J.
More informationRobust Statistics, Revisited
Robust Statistics, Revisited Ankur Moitra (MIT) joint work with Ilias Diakonikolas, Jerry Li, Gautam Kamath, Daniel Kane and Alistair Stewart CLASSIC PARAMETER ESTIMATION Given samples from an unknown
More informationThe convex algebraic geometry of linear inverse problems
The convex algebraic geometry of linear inverse problems The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published Publisher
More informationMatrix Completion with Noise
Matrix Completion with Noise 1 Emmanuel J. Candès and Yaniv Plan Applied and Computational Mathematics, Caltech, Pasadena, CA 91125 of the rapidly developing field of compressed sensing, and is already
More informationUniqueness Conditions For Low-Rank Matrix Recovery
Claremont Colleges Scholarship @ Claremont CMC Faculty Publications and Research CMC Faculty Scholarship 3-28-2011 Uniqueness Conditions For Low-Rank Matrix Recovery Yonina C. Eldar Israel Institute of
More informationLatent Variable Graphical Model Selection Via Convex Optimization
Latent Variable Graphical Model Selection Via Convex Optimization The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Citation As Published
More informationGeneralized Higher-Order Tensor Decomposition via Parallel ADMM
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence Generalized Higher-Order Tensor Decomposition via Parallel ADMM Fanhua Shang 1, Yuanyuan Liu 2, James Cheng 1 1 Department of
More informationComplexity of Deciding Convexity in Polynomial Optimization
Complexity of Deciding Convexity in Polynomial Optimization Amir Ali Ahmadi Joint work with: Alex Olshevsky, Pablo A. Parrilo, and John N. Tsitsiklis Laboratory for Information and Decision Systems Massachusetts
More informationProperties of Matrices and Operations on Matrices
Properties of Matrices and Operations on Matrices A common data structure for statistical analysis is a rectangular array or matris. Rows represent individual observational units, or just observations,
More informationOptimisation Combinatoire et Convexe.
Optimisation Combinatoire et Convexe. Low complexity models, l 1 penalties. A. d Aspremont. M1 ENS. 1/36 Today Sparsity, low complexity models. l 1 -recovery results: three approaches. Extensions: matrix
More informationHigh-dimensional Statistical Models
High-dimensional Statistical Models Pradeep Ravikumar UT Austin MLSS 2014 1 Curse of Dimensionality Statistical Learning: Given n observations from p(x; θ ), where θ R p, recover signal/parameter θ. For
More informationMatrix Completion from Noisy Entries
Matrix Completion from Noisy Entries Raghunandan H. Keshavan, Andrea Montanari, and Sewoong Oh Abstract Given a matrix M of low-rank, we consider the problem of reconstructing it from noisy observations
More informationRecovery of Simultaneously Structured Models using Convex Optimization
Recovery of Simultaneously Structured Models using Convex Optimization Maryam Fazel University of Washington Joint work with: Amin Jalali (UW), Samet Oymak and Babak Hassibi (Caltech) Yonina Eldar (Technion)
More informationTENSOR DECOMPOSITIONS AND THEIR APPLICATIONS
TENSOR DECOMPOSITIONS AND THEIR APPLICATIONS ANKUR MOITRA MASSACHUSETTS INSTITUTE OF TECHNOLOGY SPEARMAN S HYPOTHESIS Charles Spearman (1904): There are two types of intelligence, educ%ve and reproduc%ve
More informationFast 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 informationFactor Matrix Trace Norm Minimization for Low-Rank Tensor Completion
Factor Matrix Trace Norm Minimization for Low-Rank Tensor Completion Yuanyuan Liu Fanhua Shang Hong Cheng James Cheng Hanghang Tong Abstract Most existing low-n-rank imization algorithms for tensor completion
More informationMatrix Completion for Structured Observations
Matrix Completion for Structured Observations Denali Molitor Department of Mathematics University of California, Los ngeles Los ngeles, C 90095, US Email: dmolitor@math.ucla.edu Deanna Needell Department
More informationConditioning and illposedness of tensor approximations
Conditioning and illposedness of tensor approximations and why engineers should care Lek-Heng Lim MSRI Summer Graduate Workshop July 7 18, 2008 L.-H. Lim (MSRI SGW) Conditioning and illposedness July 7
More informationTensor Completion for Estimating Missing Values in Visual Data
Tensor Completion for Estimating Missing Values in Visual Data Ji Liu, Przemyslaw Musialski 2, Peter Wonka, and Jieping Ye Arizona State University VRVis Research Center 2 Ji.Liu@asu.edu, musialski@vrvis.at,
More informationA Scalable Spectral Relaxation Approach to Matrix Completion via Kronecker Products
A Scalable Spectral Relaxation Approach to Matrix Completion via Kronecker Products Hui Zhao Jiuqiang Han Naiyan Wang Congfu Xu Zhihua Zhang Department of Automation, Xi an Jiaotong University, Xi an,
More informationDATA MINING LECTURE 8. Dimensionality Reduction PCA -- SVD
DATA MINING LECTURE 8 Dimensionality Reduction PCA -- SVD The curse of dimensionality Real data usually have thousands, or millions of dimensions E.g., web documents, where the dimensionality is the vocabulary
More informationAn 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 informationExact Low Tubal Rank Tensor Recovery from Gaussian Measurements
Exact Low Tubal Rank Tensor Recovery from Gaussian Measurements Canyi Lu, Jiashi Feng 2, Zhouchen Li,4 Shuicheng Yan 5,2 Department of Electrical and Computer Engineering, Carnegie Mellon University 2
More informationLinear Algebra. Session 12
Linear Algebra. Session 12 Dr. Marco A Roque Sol 08/01/2017 Example 12.1 Find the constant function that is the least squares fit to the following data x 0 1 2 3 f(x) 1 0 1 2 Solution c = 1 c = 0 f (x)
More informationTighter Low-rank Approximation via Sampling the Leveraged Element
Tighter Low-rank Approximation via Sampling the Leveraged Element Srinadh Bhojanapalli The University of Texas at Austin bsrinadh@utexas.edu Prateek Jain Microsoft Research, India prajain@microsoft.com
More information