Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization
|
|
- Teresa Griffith
- 5 years ago
- Views:
Transcription
1 Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization Nicolas Gillis Department of Mathematics and Operational Research Université de Mons, Belgium Joint work with Stephen Vavasis (U. of Waterloo) itwist 14 itwist 14 SDP Preconditioning for Separable NMF 1
2 Outline 1. Why Nonnegative Matrix Factorization (NMF)? Definition, motivations & applications 2. How to Solve Nonnegative Matrix Factorization (NMF)? A subclass of efficiently solvable NMF problems (separable NMF) Projection methods SDP-based Preconditioning itwist 14 SDP Preconditioning for Separable NMF 2
3 Part 1 Why? itwist 14 SDP Preconditioning for Separable NMF 3
4 Nonnegative Matrix Factorization (NMF) Given a matrix M R p n + and a factorization rank r min(p, n), find U R p r and V R r n such that min M UV U 0,V 0 2 F = (M UV ) 2 ij. (NMF) i,j NMF is a linear dimensionality reduction technique for nonnegative data : M(:, i) }{{} 0 r k=1 U(:, k) }{{} 0 V (k, i) }{{} 0 for all i. Why nonnegativity? Interpretability: Nonnegativity constraints lead to easily interpretable factors (and a sparse and part-based representation). Many applications. image processing, text mining, hyperspectral unmixing, community detection, clustering, etc. itwist 14 SDP Preconditioning for Separable NMF 4
5 Nonnegative Matrix Factorization (NMF) Given a matrix M R p n + and a factorization rank r min(p, n), find U R p r and V R r n such that min M UV U 0,V 0 2 F = (M UV ) 2 ij. (NMF) i,j NMF is a linear dimensionality reduction technique for nonnegative data : M(:, i) }{{} 0 r k=1 U(:, k) }{{} 0 V (k, i) }{{} 0 for all i. Why nonnegativity? Interpretability: Nonnegativity constraints lead to easily interpretable factors (and a sparse and part-based representation). Many applications. image processing, text mining, hyperspectral unmixing, community detection, clustering, etc. itwist 14 SDP Preconditioning for Separable NMF 4
6 Nonnegative Matrix Factorization (NMF) Given a matrix M R p n + and a factorization rank r min(p, n), find U R p r and V R r n such that min M UV U 0,V 0 2 F = (M UV ) 2 ij. (NMF) i,j NMF is a linear dimensionality reduction technique for nonnegative data : M(:, i) }{{} 0 r k=1 U(:, k) }{{} 0 V (k, i) }{{} 0 for all i. Why nonnegativity? Interpretability: Nonnegativity constraints lead to easily interpretable factors (and a sparse and part-based representation). Many applications. image processing, text mining, hyperspectral unmixing, community detection, clustering, etc. itwist 14 SDP Preconditioning for Separable NMF 4
7 Example 1: topic recovery and document classification Basis elements allow to recover the different topics; Weights allow to assign each text to its corresponding topics. itwist 14 SDP Preconditioning for Separable NMF 5
8 Example 1: topic recovery and document classification Basis elements allow to recover the different topics; Weights allow to assign each text to its corresponding topics. itwist 14 SDP Preconditioning for Separable NMF 5
9 Example 1: topic recovery and document classification Basis elements allow to recover the different topics; Weights allow to assign each text to its corresponding topics. itwist 14 SDP Preconditioning for Separable NMF 5
10 Exemple 2: feature extraction and classification U 0 constraints the basis elements to be nonnegative. Moreover V 0 imposes an additive reconstruction. The basis elements extract facial features such as eyes, nose and lips. itwist 14 SDP Preconditioning for Separable NMF 6
11 Exemple 2: feature extraction and classification U 0 constraints the basis elements to be nonnegative. Moreover V 0 imposes an additive reconstruction. The basis elements extract facial features such as eyes, nose and lips. itwist 14 SDP Preconditioning for Separable NMF 6
12 Exemple 2: feature extraction and classification U 0 constraints the basis elements to be nonnegative. Moreover V 0 imposes an additive reconstruction. The basis elements extract facial features such as eyes, nose and lips. itwist 14 SDP Preconditioning for Separable NMF 6
13 Example 3: blind hyperspectral unmixing Figure : Urban hyperspectral image with 162 spectral bands and 307-by-307 pixels. itwist 14 SDP Preconditioning for Separable NMF 7
14 Example 3: blind hyperspectral unmixing Basis elements allow to recover the different materials; Weights allow to know which pixel contains which material. itwist 14 SDP Preconditioning for Separable NMF 8
15 Example 3: blind hyperspectral unmixing Basis elements allow to recover the different materials; Weights allow to know which pixel contains which material. itwist 14 SDP Preconditioning for Separable NMF 8
16 Example 3: blind hyperspectral unmixing Basis elements allow to recover the different materials; Weights allow to know which pixel contains which material. itwist 14 SDP Preconditioning for Separable NMF 8
17 Example 3: blind hyperspectral unmixing Figure : Decomposition of the Urban dataset. itwist 14 SDP Preconditioning for Separable NMF 9
18 Example 3: blind hyperspectral unmixing Figure : Decomposition of the Urban dataset. itwist 14 SDP Preconditioning for Separable NMF 9
19 Example 3: blind hyperspectral unmixing Figure : Decomposition of the Urban dataset. itwist 14 SDP Preconditioning for Separable NMF 9
20 Part 2 How? itwist 14 SDP Preconditioning for Separable NMF 10
21 Can we only solve NMF problems? Given a matrix M R p n + and a factorization rank r N, find U R p r and V R r n such that min M UV U 0,V 0 2 F = (M UV ) 2 ij. (NMF) i,j NMF is NP-hard [V09], and highly ill-posed [G12]. In practice, it is often satisfactory to use locally optimal solutions for further analysis of the data. In other words, heuristics often solve the problem efficiently with acceptable answers. Try to analyze this state of affairs by considering generative models and algorithms that can recover hidden data. [V09] Vavasis, On the Complexity of Nonnegative Matrix Factorization, SIAM J. Optim., [G12] G., Sparse and Unique Nonnegative Matrix Factorization Through Data Preprocessing, JMLR, itwist 14 SDP Preconditioning for Separable NMF 11
22 Can we only solve NMF problems? Given a matrix M R p n + and a factorization rank r N, find U R p r and V R r n such that min M UV U 0,V 0 2 F = (M UV ) 2 ij. (NMF) i,j NMF is NP-hard [V09], and highly ill-posed [G12]. In practice, it is often satisfactory to use locally optimal solutions for further analysis of the data. In other words, heuristics often solve the problem efficiently with acceptable answers. Try to analyze this state of affairs by considering generative models and algorithms that can recover hidden data. [V09] Vavasis, On the Complexity of Nonnegative Matrix Factorization, SIAM J. Optim., [G12] G., Sparse and Unique Nonnegative Matrix Factorization Through Data Preprocessing, JMLR, itwist 14 SDP Preconditioning for Separable NMF 11
23 Separability Assumption Heuristics often solve the problem efficiently with acceptable answers (usually one needs to use additional regularization on U and V ). Try to analyze this state of affairs by considering generative models and algorithms that can recover hidden data. NMF can be solved in polynomial time if M is separable (rather strong condition) [AGKM12]. Separability of M = there exists an NMF (U, V ) 0 with M = UV where each column of U is equal to a column of M. [AGKM12] Arora, Ge, Kannan, Moitra, Computing a Nonnegative Matrix Factorization Provably, STOC itwist 14 SDP Preconditioning for Separable NMF 12
24 Separability Assumption Heuristics often solve the problem efficiently with acceptable answers (usually one needs to use additional regularization on U and V ). Try to analyze this state of affairs by considering generative models and algorithms that can recover hidden data. NMF can be solved in polynomial time if M is separable (rather strong condition) [AGKM12]. Separability of M = there exists an NMF (U, V ) 0 with M = UV where each column of U is equal to a column of M. [AGKM12] Arora, Ge, Kannan, Moitra, Computing a Nonnegative Matrix Factorization Provably, STOC itwist 14 SDP Preconditioning for Separable NMF 12
25 Is separability a reasonable assumption? Text mining: for each topic, there is a pure document on that topic, or, for each topic, there is a anchor word used only by that topic. [KSK13] Kumar, Sindhwani, Kambadur, Fast Conical Hull Algorithms for Near-separable Non-Negative Matrix Factorization, ICML [A+13] Arora, Ge, Halpern, Mimno, Moitra, Sontag, Wu, Zhu, A Practical Algorithm for Topic Modeling with Provable Guarantees, ICML [DRIS13] Ding, Rohban, Ishwar, Saligrama, Topic Discovery through Data Dependent and Random Projections, ICML Hyperspectral unmixing: separability is particularly natural: for each constitutive material, there is a pure pixel containing only that material. This is the so called pure-pixel assumption. [Ma+13] Ma, Bioucas-Dias, Chan, G., Gader, Plaza, Ambikapathi, Chi, Signal Processing Perspective on Hyperspectral Unmixing, IEEE Signal Proc. Mag., General image processing: No. itwist 14 SDP Preconditioning for Separable NMF 13
26 Is separability a reasonable assumption? Text mining: for each topic, there is a pure document on that topic, or, for each topic, there is a anchor word used only by that topic. [KSK13] Kumar, Sindhwani, Kambadur, Fast Conical Hull Algorithms for Near-separable Non-Negative Matrix Factorization, ICML [A+13] Arora, Ge, Halpern, Mimno, Moitra, Sontag, Wu, Zhu, A Practical Algorithm for Topic Modeling with Provable Guarantees, ICML [DRIS13] Ding, Rohban, Ishwar, Saligrama, Topic Discovery through Data Dependent and Random Projections, ICML Hyperspectral unmixing: separability is particularly natural: for each constitutive material, there is a pure pixel containing only that material. This is the so called pure-pixel assumption. [Ma+13] Ma, Bioucas-Dias, Chan, G., Gader, Plaza, Ambikapathi, Chi, Signal Processing Perspective on Hyperspectral Unmixing, IEEE Signal Proc. Mag., General image processing: No. itwist 14 SDP Preconditioning for Separable NMF 13
27 Is separability a reasonable assumption? Text mining: for each topic, there is a pure document on that topic, or, for each topic, there is a anchor word used only by that topic. [KSK13] Kumar, Sindhwani, Kambadur, Fast Conical Hull Algorithms for Near-separable Non-Negative Matrix Factorization, ICML [A+13] Arora, Ge, Halpern, Mimno, Moitra, Sontag, Wu, Zhu, A Practical Algorithm for Topic Modeling with Provable Guarantees, ICML [DRIS13] Ding, Rohban, Ishwar, Saligrama, Topic Discovery through Data Dependent and Random Projections, ICML Hyperspectral unmixing: separability is particularly natural: for each constitutive material, there is a pure pixel containing only that material. This is the so called pure-pixel assumption. [Ma+13] Ma, Bioucas-Dias, Chan, G., Gader, Plaza, Ambikapathi, Chi, Signal Processing Perspective on Hyperspectral Unmixing, IEEE Signal Proc. Mag., General image processing: No. itwist 14 SDP Preconditioning for Separable NMF 13
28 Geometric Interpretation of Separability Using normalization, the entries of each column of M, U and V can be assumed to sum to one: for all j, M(:, j) = r U(:, k)v (k, j) where V (k, j) 0 and k=1 r V (k, j) = 1. The columns of U are the vertices of the convex hull of the columns of M. k=1 itwist 14 SDP Preconditioning for Separable NMF 14
29 Separable NMF M is r-separable M = U[I r, V ]Π, for some V 0, and some permutation matrix Π. itwist 14 SDP Preconditioning for Separable NMF 15
30 Near-Separable NMF M = U[I r, V ]Π + N, where N is noise. itwist 14 SDP Preconditioning for Separable NMF 15
31 Near-Separable NMF: Noise and Conditioning We will assume that the noise is bounded (but otherwise arbitrary): N(:, j) 2 ɛ, for all j, and some dependence on some condition number is unavoidable: itwist 14 SDP Preconditioning for Separable NMF 16
32 Near-Separable NMF: Noise and Conditioning We will assume that the noise is bounded (but otherwise arbitrary): N(:, j) 2 ɛ, for all j, and some dependence on some condition number is unavoidable: itwist 14 SDP Preconditioning for Separable NMF 16
33 Near-Separable NMF: Noise and Conditioning We will assume that the noise is bounded (but otherwise arbitrary): N(:, j) 2 ɛ, for all j, and some dependence on some condition number is unavoidable: itwist 14 SDP Preconditioning for Separable NMF 16
34 Successive Projection Algorithm (SPA) 0: Initially K =. For i = 1 : r 1: Find j such that M(:, j) is max. 2: K = K {j }. 3: M ( I uu T ) M where u = M(:,j ) M(:,j ) 2. end modified Gram-Schmidt with column pivoting. ) Theorem. If ɛ O, SPA satisfies ( σmin (U) rκ 2 (U) min M M(:, K)V O ( ɛκ 2 (U) ). V 0 Advantages. Extremely fast, no parameter. Drawbacks. Requires U to be full rank; bound is weak. [GV12] G., Vavasis, Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization, IEEE Trans. Patt. Anal. Mach. Intell. 36 (4), pp , itwist 14 SDP Preconditioning for Separable NMF 17
35 Successive Projection Algorithm (SPA) 0: Initially K =. For i = 1 : r 1: Find j such that M(:, j) is max. 2: K = K {j }. 3: M ( I uu T ) M where u = M(:,j ) M(:,j ) 2. end modified Gram-Schmidt with column pivoting. ) Theorem. If ɛ O, SPA satisfies ( σmin (U) rκ 2 (U) min M M(:, K)V O ( ɛκ 2 (U) ). V 0 Advantages. Extremely fast, no parameter. Drawbacks. Requires U to be full rank; bound is weak. [GV12] G., Vavasis, Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization, IEEE Trans. Patt. Anal. Mach. Intell. 36 (4), pp , itwist 14 SDP Preconditioning for Separable NMF 17
36 Pre-conditioning for More Robust SPA Observation. Pre-multiplying M preserves separability: P M = P (U[I r, V ] + N) = (P U) [I, V ] + P N. Ideally, P = U 1 so that κ(p U) = 1 (assuming p = r). Solving the minimum volume ellipsoid centered at the origin and containing all the columns of M (which is SDP representable) min A S r + log det(a) 1 s.t. m j T A m j 1 j, allows to approximate U 1 : in fact, A (UU T ) 1. Theorem. If ɛ O ( σmin (U) r r ), preconditioned SPA satisfies min M M(:, K)V O (ɛκ(u)). V 0 [GV13] G., Vavasis, SDP-based Preconditioning for More Robust Near-Separable NMF, arxiv: itwist 14 SDP Preconditioning for Separable NMF 18
37 Pre-conditioning for More Robust SPA Observation. Pre-multiplying M preserves separability: P M = P (U[I r, V ] + N) = (P U) [I, V ] + P N. Ideally, P = U 1 so that κ(p U) = 1 (assuming p = r). Solving the minimum volume ellipsoid centered at the origin and containing all the columns of M (which is SDP representable) min A S r + log det(a) 1 s.t. m j T A m j 1 j, allows to approximate U 1 : in fact, A (UU T ) 1. Theorem. If ɛ O ( σmin (U) r r ), preconditioned SPA satisfies min M M(:, K)V O (ɛκ(u)). V 0 [GV13] G., Vavasis, SDP-based Preconditioning for More Robust Near-Separable NMF, arxiv: itwist 14 SDP Preconditioning for Separable NMF 18
38 Pre-conditioning for More Robust SPA Observation. Pre-multiplying M preserves separability: P M = P (U[I r, V ] + N) = (P U) [I, V ] + P N. Ideally, P = U 1 so that κ(p U) = 1 (assuming p = r). Solving the minimum volume ellipsoid centered at the origin and containing all the columns of M (which is SDP representable) min A S r + log det(a) 1 s.t. m j T A m j 1 j, allows to approximate U 1 : in fact, A (UU T ) 1. Theorem. If ɛ O ( σmin (U) r r ), preconditioned SPA satisfies min M M(:, K)V O (ɛκ(u)). V 0 [GV13] G., Vavasis, SDP-based Preconditioning for More Robust Near-Separable NMF, arxiv: itwist 14 SDP Preconditioning for Separable NMF 18
39 Pre-conditioning for More Robust SPA Observation. Pre-multiplying M preserves separability: P M = P (U[I r, V ] + N) = (P U) [I, V ] + P N. Ideally, P = U 1 so that κ(p U) = 1 (assuming p = r). Solving the minimum volume ellipsoid centered at the origin and containing all the columns of M (which is SDP representable) min A S r + log det(a) 1 s.t. m j T A m j 1 j, allows to approximate U 1 : in fact, A (UU T ) 1. Theorem. If ɛ O ( σmin (U) r r ), preconditioned SPA satisfies min M M(:, K)V O (ɛκ(u)). V 0 [GV13] G., Vavasis, SDP-based Preconditioning for More Robust Near-Separable NMF, arxiv: itwist 14 SDP Preconditioning for Separable NMF 18
40 Geometric Interpretation Figure : Geometric Interpretation of the SDP-based Preconditioning. itwist 14 SDP Preconditioning for Separable NMF 19
41 Synthetic data sets Each entry of U R uniform in [0, 1]; each column normalized. The other columns of M are the middle points of the columns of U (hence there are ( 20 2 ) = 190). The noise moves the middle points toward the outside of the convex hull of the column of U. itwist 14 SDP Preconditioning for Separable NMF 20
42 Synthetic data sets Each entry of U R uniform in [0, 1]; each column normalized. The other columns of M are the middle points of the columns of U (hence there are ( 20 2 ) = 190). The noise moves the middle points toward the outside of the convex hull of the column of U. itwist 14 SDP Preconditioning for Separable NMF 20
43 Results for the synthetic data sets Figure : Average of the percentage of columns correctly extracted depending on the noise level (for each noise level, 10 matrices are generated). itwist 14 SDP Preconditioning for Separable NMF 21
44 Hubble telescope hyperspectral image Figure : Sample of images for the Hubble telescope hyperspectral image with 100 spectral bands and pixels. itwist 14 SDP Preconditioning for Separable NMF 22
45 Hubble telescope hyperspectral image Figure : Spectral signatures extracted by SPA, corresponding to constitutive materials (matrix U with κ(u) = 115). itwist 14 SDP Preconditioning for Separable NMF 22
46 Hubble telescope hyperspectral image Figure : Reconstructed abundance maps (matrix V ). itwist 14 SDP Preconditioning for Separable NMF 22
47 Hubble telescope with blur and noise Figure : Sample of images for the Hubble telescope. itwist 14 SDP Preconditioning for Separable NMF 23
48 Hubble telescope with blur and noise Figure : Spectral signatures extracted by SPA, corresponding to constitutive materials (matrix U). itwist 14 SDP Preconditioning for Separable NMF 23
49 Hubble telescope with blur and noise Figure : Reconstructed abundance maps (matrix V ). With the blur and noise, SPA fails to identify good columns (two correspond to the same material). itwist 14 SDP Preconditioning for Separable NMF 23
50 Hubble telescope with blur and noise Figure : Spectral signatures extracted by preconditioned SPA, corresponding to constitutive materials (matrix U). itwist 14 SDP Preconditioning for Separable NMF 24
51 Hubble telescope with blur and noise Figure : Reconstructed abundance maps (matrix V ). With the blur and noise, preconditioned SPA is able to identify the right columns. itwist 14 SDP Preconditioning for Separable NMF 24
52 Conclusion 1. Nonnegative matrix factorization (NMF) Easily interpretable linear dimensionality reduction technique for nonnegative data, with many applications 2. Separable NMF Separability makes NMF problems efficiently solvable Need for fast, practical and robust algorithms SPA, a fast and robust recursive algorithm for separable NMF (simple to implement, no parameter tuning, no need to recompute the solution from scratch when r is changed). Pre-conditioning allows to make it much more robust to noise. Other robust algorithms, e.g., based on linear optimization (G. and Luce, Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization, JMLR, 2014). itwist 14 SDP Preconditioning for Separable NMF 25
53 Conclusion 1. Nonnegative matrix factorization (NMF) Easily interpretable linear dimensionality reduction technique for nonnegative data, with many applications 2. Separable NMF Separability makes NMF problems efficiently solvable Need for fast, practical and robust algorithms SPA, a fast and robust recursive algorithm for separable NMF (simple to implement, no parameter tuning, no need to recompute the solution from scratch when r is changed). Pre-conditioning allows to make it much more robust to noise. Other robust algorithms, e.g., based on linear optimization (G. and Luce, Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization, JMLR, 2014). itwist 14 SDP Preconditioning for Separable NMF 25
54 Conclusion 1. Nonnegative matrix factorization (NMF) Easily interpretable linear dimensionality reduction technique for nonnegative data, with many applications 2. Separable NMF Separability makes NMF problems efficiently solvable Need for fast, practical and robust algorithms SPA, a fast and robust recursive algorithm for separable NMF (simple to implement, no parameter tuning, no need to recompute the solution from scratch when r is changed). Pre-conditioning allows to make it much more robust to noise. Other robust algorithms, e.g., based on linear optimization (G. and Luce, Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization, JMLR, 2014). itwist 14 SDP Preconditioning for Separable NMF 25
55 Thank you for your attention! Code and papers available on [GV13] G., Vavasis, SDP-based Preconditioning for More Robust Near-Separable NMF, arxiv: itwist 14 SDP Preconditioning for Separable NMF 26
Linear 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 informationA Practical Algorithm for Topic Modeling with Provable Guarantees
1 A Practical Algorithm for Topic Modeling with Provable Guarantees Sanjeev Arora, Rong Ge, Yoni Halpern, David Mimno, Ankur Moitra, David Sontag, Yichen Wu, Michael Zhu Reviewed by Zhao Song December
More informationOn Identifiability of Nonnegative Matrix Factorization
On Identifiability of Nonnegative Matrix Factorization Xiao Fu, Kejun Huang, and Nicholas D. Sidiropoulos Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, 55455,
More informationRobust Spectral Inference for Joint Stochastic Matrix Factorization
Robust Spectral Inference for Joint Stochastic Matrix Factorization Kun Dong Cornell University October 20, 2016 K. Dong (Cornell University) Robust Spectral Inference for Joint Stochastic Matrix Factorization
More informationSemidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization
Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization Nicolas Gillis Faculté Polytechnique, Université de Mons Department of Mathematics and Operational
More informationRobust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization
Journal of Machine Learning Research 5 (204) 249-280 Submitted 3/3; Revised 0/3; Published 4/4 Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization Nicolas Gillis Department
More informationONP-MF: An Orthogonal Nonnegative Matrix Factorization Algorithm with Application to Clustering
ONP-MF: An Orthogonal Nonnegative Matrix Factorization Algorithm with Application to Clustering Filippo Pompili 1, Nicolas Gillis 2, P.-A. Absil 2,andFrançois Glineur 2,3 1- University of Perugia, Department
More informationIntersecting Faces: Non-negative Matrix Factorization With New Guarantees
Rong Ge Microsoft Research New England James Zou Microsoft Research New England RONGGE@MICROSOFT.COM JAZO@MICROSOFT.COM Abstract Non-negative matrix factorization (NMF) is a natural model of admixture
More informationENGG5781 Matrix Analysis and Computations Lecture 10: Non-Negative Matrix Factorization and Tensor Decomposition
ENGG5781 Matrix Analysis and Computations Lecture 10: Non-Negative Matrix Factorization and Tensor Decomposition Wing-Kin (Ken) Ma 2017 2018 Term 2 Department of Electronic Engineering The Chinese University
More informationNon-negative Matrix Factorization under Heavy Noise
Non-negative Matrix Factorization under Heavy Noise Chiranjib Bhattacharyya CHIRU@CSA.IISC.ERNET.IN Navin Goyal NAVINGO@MICROSOFT.COM Ravindran Kannan KANNAN@MICROSOFT.COM Jagdeep Pani PANI.JAGDEEP@GMAIL.COM
More informationCS264: Beyond Worst-Case Analysis Lecture #15: Topic Modeling and Nonnegative Matrix Factorization
CS264: Beyond Worst-Case Analysis Lecture #15: Topic Modeling and Nonnegative Matrix Factorization Tim Roughgarden February 28, 2017 1 Preamble This lecture fulfills a promise made back in Lecture #1,
More informationProvable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations Yuanzhi Li 1 Yingyu Liang 1 In this paper, we provide a theoretical analysis of a natural algorithm
More informationarxiv: v2 [stat.ml] 7 Mar 2014
The Why and How of Nonnegative Matrix Factorization arxiv:1401.5226v2 [stat.ml] 7 Mar 2014 Nicolas Gillis Department of Mathematics and Operational Research Faculté Polytechnique, Université de Mons Rue
More informationarxiv: v3 [math.oc] 16 Aug 2017
A Fast Gradient Method for Nonnegative Sparse Regression with Self Dictionary Nicolas Gillis Robert Luce arxiv:1610.01349v3 [math.oc] 16 Aug 2017 Abstract A nonnegative matrix factorization (NMF) can be
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 informationSolving 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 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 informationPhil Schniter. Collaborators: Jason Jeremy and Volkan
Bilinear Generalized Approximate Message Passing (BiG-AMP) for Dictionary Learning Phil Schniter Collaborators: Jason Parker @OSU, Jeremy Vila @OSU, and Volkan Cehver @EPFL With support from NSF CCF-,
More informationNON-NEGATIVE SPARSE CODING
NON-NEGATIVE SPARSE CODING Patrik O. Hoyer Neural Networks Research Centre Helsinki University of Technology P.O. Box 9800, FIN-02015 HUT, Finland patrik.hoyer@hut.fi To appear in: Neural Networks for
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 informationPhase Retrieval from Local Measurements: Deterministic Measurement Constructions and Efficient Recovery Algorithms
Phase Retrieval from Local Measurements: Deterministic Measurement Constructions and Efficient Recovery Algorithms Aditya Viswanathan Department of Mathematics and Statistics adityavv@umich.edu www-personal.umich.edu/
More informationarxiv: v2 [stat.ml] 21 Oct 2013
Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization arxiv:302.4385v2 [stat.ml] 2 Oct 203 Nicolas Gillis Department of Mathematics and Operational Research Faculté Polytechnique,
More informationA fast randomized algorithm for approximating an SVD of a matrix
A fast randomized algorithm for approximating an SVD of a matrix Joint work with Franco Woolfe, Edo Liberty, and Vladimir Rokhlin Mark Tygert Program in Applied Mathematics Yale University Place July 17,
More informationA Practical Algorithm for Topic Modeling with Provable Guarantees
Sanjeev Arora Rong Ge Yoni Halpern David Mimno Ankur Moitra David Sontag Yichen Wu Michael Zhu arora@cs.princeton.edu rongge@cs.princeton.edu halpern@cs.nyu.edu mimno@cs.princeton.edu moitra@ias.edu dsontag@cs.nyu.edu
More informationCANONICAL POLYADIC DECOMPOSITION OF HYPERSPECTRAL PATCH TENSORS
th European Signal Processing Conference (EUSIPCO) CANONICAL POLYADIC DECOMPOSITION OF HYPERSPECTRAL PATCH TENSORS M.A. Veganzones a, J.E. Cohen a, R. Cabral Farias a, K. Usevich a, L. Drumetz b, J. Chanussot
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 informationScalable Subspace Clustering
Scalable Subspace Clustering René Vidal Center for Imaging Science, Laboratory for Computational Sensing and Robotics, Institute for Computational Medicine, Department of Biomedical Engineering, Johns
More informationLog-determinant Non-negative Matrix Factorization via Successive Trace Approximation
Log-determinant Non-negative Matrix Factorization via Successive Trace Approximation Optimizing an optimization algorithm Andersen Ang Mathématique et recherche opérationnelle UMONS, Belgium Email: manshun.ang@umons.ac.be
More information1 Introduction to constrained low-rank matrix approximations. Volume 25 Number 1 January
Volume 25 Number 1 January 2017 7 Introduction to Nonnegative Matrix Factorization Nicolas Gillis Department of Mathematics and Operational Research University of Mons, Rue de Houdain 9, 7000 Mons, Belgium
More informationINFORMED SPLIT GRADIENT NON-NEGATIVE MATRIX FACTORIZATION USING HUBER COST FUNCTION FOR SOURCE APPORTIONMENT
INFORMED SPLIT GRADIENT NON-NEGATIVE MATRIX FACTORIZATION USING HUBER COST FUNCTION FOR SOURCE APPORTIONMENT Robert Chreiky, Gilles Delmaire, Matthieu Puigt, Gilles Roussel, and Antoine Abche Univ. Littoral
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 informationNONNEGATIVE matrix factorization (NMF) has become
1 Efficient and Non-Convex Coordinate Descent for Symmetric Nonnegative Matrix Factorization Arnaud Vandaele 1, Nicolas Gillis 1, Qi Lei 2, Kai Zhong 2, and Inderjit Dhillon 2,3, Fellow, IEEE 1 Department
More informationJointly Clustering Rows and Columns of Binary Matrices: Algorithms and Trade-offs
Jointly Clustering Rows and Columns of Binary Matrices: Algorithms and Trade-offs Jiaming Xu Joint work with Rui Wu, Kai Zhu, Bruce Hajek, R. Srikant, and Lei Ying University of Illinois, Urbana-Champaign
More informationAppendix A. Proof to Theorem 1
Appendix A Proof to Theorem In this section, we prove the sample complexity bound given in Theorem The proof consists of three main parts In Appendix A, we prove perturbation lemmas that bound the estimation
More informationN-mode Analysis (Tensor Framework) Behrouz Saghafi
N-mode Analysis (Tensor Framework) Behrouz Saghafi N-mode Analysis (Tensor Framework) Drawback of 1-mode analysis (e.g. PCA): Captures the variance among just a single factor Our training set contains
More informationarxiv: v1 [cs.na] 1 Oct 2017
Efficient Preconditioning for Noisy Separable NMFs by Successive Projection Based Low-Rank Approximations Tomohiko Mizutani Mirai Tanaka arxiv:1710.00387v1 [cs.na] 1 Oct 2017 August 27, 2018 Abstract The
More informationCardinality-Constrained Clustering and Outlier Detection via Conic Optimization
Computational Management Science 2017 Cardinality-Constrained Clustering and Outlier Detection via Conic Optimization Presented by Kilian Schindler École Polytechnique Fédérale de Lausanne Joint work with
More informationScience Insights: An International Journal
Available online at http://www.urpjournals.com Science Insights: An International Journal Universal Research Publications. All rights reserved ISSN 2277 3835 Original Article Object Recognition using Zernike
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 informationGraph 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 informationAlgorithms Reading Group Notes: Provable Bounds for Learning Deep Representations
Algorithms Reading Group Notes: Provable Bounds for Learning Deep Representations Joshua R. Wang November 1, 2016 1 Model and Results Continuing from last week, we again examine provable algorithms for
More informationIntroduction to the Tensor Train Decomposition and Its Applications in Machine Learning
Introduction to the Tensor Train Decomposition and Its Applications in Machine Learning Anton Rodomanov Higher School of Economics, Russia Bayesian methods research group (http://bayesgroup.ru) 14 March
More informationA quadratic programming approach to find faces in robust nonnegative matrix factorization
A quadratic programming approach to find faces in robust nonnegative matrix factorization by Sai Mali Ananthanarayanan A thesis presented to the University of Waterloo in fulfillment of the thesis requirement
More informationSPARSE signal representations have gained popularity in recent
6958 IEEE TRANSACTIONS ON INFORMATION THEORY, VOL. 57, NO. 10, OCTOBER 2011 Blind Compressed Sensing Sivan Gleichman and Yonina C. Eldar, Senior Member, IEEE Abstract The fundamental principle underlying
More informationNonnegative Matrix Factorization Clustering on Multiple Manifolds
Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10) Nonnegative Matrix Factorization Clustering on Multiple Manifolds Bin Shen, Luo Si Department of Computer Science,
More informationA Quantum Interior Point Method for LPs and SDPs
A Quantum Interior Point Method for LPs and SDPs Iordanis Kerenidis 1 Anupam Prakash 1 1 CNRS, IRIF, Université Paris Diderot, Paris, France. September 26, 2018 Semi Definite Programs A Semidefinite Program
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 informationMatrix Decomposition in Privacy-Preserving Data Mining JUN ZHANG DEPARTMENT OF COMPUTER SCIENCE UNIVERSITY OF KENTUCKY
Matrix Decomposition in Privacy-Preserving Data Mining JUN ZHANG DEPARTMENT OF COMPUTER SCIENCE UNIVERSITY OF KENTUCKY OUTLINE Why We Need Matrix Decomposition SVD (Singular Value Decomposition) NMF (Nonnegative
More informationInterpretable Nonnegative Matrix Decompositions
27 August 2008 Outline 1 Introduction 2 Definitions 3 Algorithms and Complexity 4 Experiments Synthetic Data Real Data 5 Conclusions Outline 1 Introduction 2 Definitions 3 Algorithms and Complexity 4 Experiments
More informationSDP Relaxations for MAXCUT
SDP Relaxations for MAXCUT from Random Hyperplanes to Sum-of-Squares Certificates CATS @ UMD March 3, 2017 Ahmed Abdelkader MAXCUT SDP SOS March 3, 2017 1 / 27 Overview 1 MAXCUT, Hardness and UGC 2 LP
More informationDropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization
Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization Zhihui Zhu Mathematical Institute for Data Science Johns Hopkins University Baltimore, MD, USA zzhu29@jhu.edu Kai Liu Department of
More informationFacial reduction for Euclidean distance matrix problems
Facial reduction for Euclidean distance matrix problems Nathan Krislock Department of Mathematical Sciences Northern Illinois University, USA Distance Geometry: Theory and Applications DIMACS Center, Rutgers
More informationAn Introduction to Spectral Learning
An Introduction to Spectral Learning Hanxiao Liu November 8, 2013 Outline 1 Method of Moments 2 Learning topic models using spectral properties 3 Anchor words Preliminaries X 1,, X n p (x; θ), θ = (θ 1,
More informationk-means Clustering via the Frank-Wolfe Algorithm
k-means Clustering via the Frank-Wolfe Algorithm Christian Bauckhage B-IT, University of Bonn, Bonn, Germany Fraunhofer IAIS, Sankt Augustin, Germany http://multimedia-pattern-recognition.info Abstract.
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 informationSparse Solutions of an Undetermined Linear System
1 Sparse Solutions of an Undetermined Linear System Maddullah Almerdasy New York University Tandon School of Engineering arxiv:1702.07096v1 [math.oc] 23 Feb 2017 Abstract This work proposes a research
More informationDonald Goldfarb IEOR Department Columbia University UCLA Mathematics Department Distinguished Lecture Series May 17 19, 2016
Optimization for Tensor Models Donald Goldfarb IEOR Department Columbia University UCLA Mathematics Department Distinguished Lecture Series May 17 19, 2016 1 Tensors Matrix Tensor: higher-order matrix
More informationMajorization Minimization (MM) and Block Coordinate Descent (BCD)
Majorization Minimization (MM) and Block Coordinate Descent (BCD) Wing-Kin (Ken) Ma Department of Electronic Engineering, The Chinese University Hong Kong, Hong Kong ELEG5481, Lecture 15 Acknowledgment:
More informationAutomatic Rank Determination in Projective Nonnegative Matrix Factorization
Automatic Rank Determination in Projective Nonnegative Matrix Factorization Zhirong Yang, Zhanxing Zhu, and Erkki Oja Department of Information and Computer Science Aalto University School of Science and
More informationSemidefinite Facial Reduction for Euclidean Distance Matrix Completion
Semidefinite Facial Reduction for Euclidean Distance Matrix Completion Nathan Krislock, Henry Wolkowicz Department of Combinatorics & Optimization University of Waterloo First Alpen-Adria Workshop on Optimization
More informationELE539A: Optimization of Communication Systems Lecture 15: Semidefinite Programming, Detection and Estimation Applications
ELE539A: Optimization of Communication Systems Lecture 15: Semidefinite Programming, Detection and Estimation Applications Professor M. Chiang Electrical Engineering Department, Princeton University March
More informationPreserving Privacy in Data Mining using Data Distortion Approach
Preserving Privacy in Data Mining using Data Distortion Approach Mrs. Prachi Karandikar #, Prof. Sachin Deshpande * # M.E. Comp,VIT, Wadala, University of Mumbai * VIT Wadala,University of Mumbai 1. prachiv21@yahoo.co.in
More informationarxiv: v2 [math.oc] 10 Feb 2014
Two Algorithms for Orthogonal Nonnegative Matrix Factorization with Application to Clustering Filippo Pompili Nicolas Gillis P.-A. Absil François Glineur arxiv:1201.0901v2 [math.oc] 10 Feb 2014 Abstract
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 informationPHASE RETRIEVAL OF SPARSE SIGNALS FROM MAGNITUDE INFORMATION. A Thesis MELTEM APAYDIN
PHASE RETRIEVAL OF SPARSE SIGNALS FROM MAGNITUDE INFORMATION A Thesis by MELTEM APAYDIN Submitted to the Office of Graduate and Professional Studies of Texas A&M University in partial fulfillment of the
More informationInteraction on spectral data with: Kira Abercromby (NASA-Houston) Related Papers at:
Low-Rank Nonnegative Factorizations for Spectral Imaging Applications Bob Plemmons Wake Forest University Collaborators: Christos Boutsidis (U. Patras), Misha Kilmer (Tufts), Peter Zhang, Paul Pauca, (WFU)
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 informationNew Coherence and RIP Analysis for Weak. Orthogonal Matching Pursuit
New Coherence and RIP Analysis for Wea 1 Orthogonal Matching Pursuit Mingrui Yang, Member, IEEE, and Fran de Hoog arxiv:1405.3354v1 [cs.it] 14 May 2014 Abstract In this paper we define a new coherence
More informationarxiv: v2 [stat.ml] 30 Apr 2018
Randomized Nonnegative Matrix Factorization N. Benjamin Erichson University of Washington Ariana Mendible University of Washington Sophie Wihlborn Fidelity International J. Nathan Kutz University of Washington
More informationIntroduction to Convex Optimization
Introduction to Convex Optimization Daniel P. Palomar Hong Kong University of Science and Technology (HKUST) ELEC5470 - Convex Optimization Fall 2018-19, HKUST, Hong Kong Outline of Lecture Optimization
More informationScalable Completion of Nonnegative Matrices with the Separable Structure
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-6) Scalable Completion of Nonnegative Matrices with the Separable Structure Xiyu Yu, Wei Bian, Dacheng Tao Center for Quantum
More informationDiscriminative Direction for Kernel Classifiers
Discriminative Direction for Kernel Classifiers Polina Golland Artificial Intelligence Lab Massachusetts Institute of Technology Cambridge, MA 02139 polina@ai.mit.edu Abstract In many scientific and engineering
More informationRank Selection in Low-rank Matrix Approximations: A Study of Cross-Validation for NMFs
Rank Selection in Low-rank Matrix Approximations: A Study of Cross-Validation for NMFs Bhargav Kanagal Department of Computer Science University of Maryland College Park, MD 277 bhargav@cs.umd.edu Vikas
More informationSome preconditioners for systems of linear inequalities
Some preconditioners for systems of linear inequalities Javier Peña Vera oshchina Negar Soheili June 0, 03 Abstract We show that a combination of two simple preprocessing steps would generally improve
More informationOverlapping Variable Clustering with Statistical Guarantees and LOVE
with Statistical Guarantees and LOVE Department of Statistical Science Cornell University WHOA-PSI, St. Louis, August 2017 Joint work with Mike Bing, Yang Ning and Marten Wegkamp Cornell University, Department
More informationSparsity-Preserving Difference of Positive Semidefinite Matrix Representation of Indefinite Matrices
Sparsity-Preserving Difference of Positive Semidefinite Matrix Representation of Indefinite Matrices Jaehyun Park June 1 2016 Abstract We consider the problem of writing an arbitrary symmetric matrix as
More informationAn 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 informationData Mining and Matrices
Data Mining and Matrices 08 Boolean Matrix Factorization Rainer Gemulla, Pauli Miettinen June 13, 2013 Outline 1 Warm-Up 2 What is BMF 3 BMF vs. other three-letter abbreviations 4 Binary matrices, tiles,
More informationA ROBUST TEST FOR NONLINEAR MIXTURE DETECTION IN HYPERSPECTRAL IMAGES
A ROBUST TEST FOR NONLINEAR MIXTURE DETECTION IN HYPERSPECTRAL IMAGES Y. Altmann, N. Dobigeon and J-Y. Tourneret University of Toulouse IRIT-ENSEEIHT Toulouse, France J.C.M. Bermudez Federal University
More informationL26: Advanced dimensionality reduction
L26: Advanced dimensionality reduction The snapshot CA approach Oriented rincipal Components Analysis Non-linear dimensionality reduction (manifold learning) ISOMA Locally Linear Embedding CSCE 666 attern
More informationAlgorithmic Aspects of Machine Learning. Ankur Moitra
Algorithmic Aspects of Machine Learning Ankur Moitra Contents Contents i Preface v 1 Introduction 3 2 Nonnegative Matrix Factorization 7 2.1 Introduction................................ 7 2.2 Algebraic
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 informationMath 520 Exam 2 Topic Outline Sections 1 3 (Xiao/Dumas/Liaw) Spring 2008
Math 520 Exam 2 Topic Outline Sections 1 3 (Xiao/Dumas/Liaw) Spring 2008 Exam 2 will be held on Tuesday, April 8, 7-8pm in 117 MacMillan What will be covered The exam will cover material from the lectures
More informationA convex model for non-negative matrix factorization and dimensionality reduction on physical space
A convex model for non-negative matrix factorization and dimensionality reduction on physical space Ernie Esser Joint work with Michael Möller, Stan Osher, Guillermo Sapiro and Jack Xin University of California
More informationSignal Recovery from Permuted Observations
EE381V Course Project Signal Recovery from Permuted Observations 1 Problem Shanshan Wu (sw33323) May 8th, 2015 We start with the following problem: let s R n be an unknown n-dimensional real-valued signal,
More informationAnalysis of NIR spectroscopy data for blend uniformity using semi-nonnegative Matrix Factorization
Analysis of NIR spectroscopy data for blend uniformity using seminonnegative Matrix Factorization Nicolas Sauwen 1, Adriaan Blommaert 1, Tatsiana Khamiakova 2, Michel Thiel 2, Jan Dijkmans 2, Ana Tavares
More informationTopic Discovery through Data Dependent and Random Projections
Weicong Ding dingwc@bu.edu Mohammad H. Rohban mhrohban@bu.edu Prakash Ishwar pi@bu.edu Venkatesh Saligrama srv@bu.edu Department of Electrical & Computer Engineering, Boston University, Boston, MA, USA
More informationSparse and Robust Optimization and Applications
Sparse and and Statistical Learning Workshop Les Houches, 2013 Robust Laurent El Ghaoui with Mert Pilanci, Anh Pham EECS Dept., UC Berkeley January 7, 2013 1 / 36 Outline Sparse Sparse Sparse Probability
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 informationCertifying the Global Optimality of Graph Cuts via Semidefinite Programming: A Theoretic Guarantee for Spectral Clustering
Certifying the Global Optimality of Graph Cuts via Semidefinite Programming: A Theoretic Guarantee for Spectral Clustering Shuyang Ling Courant Institute of Mathematical Sciences, NYU Aug 13, 2018 Joint
More informationA randomized algorithm for approximating the SVD of a matrix
A randomized algorithm for approximating the SVD of a matrix Joint work with Per-Gunnar Martinsson (U. of Colorado) and Vladimir Rokhlin (Yale) Mark Tygert Program in Applied Mathematics Yale University
More informationLimitations in Approximating RIP
Alok Puranik Mentor: Adrian Vladu Fifth Annual PRIMES Conference, 2015 Outline 1 Background The Problem Motivation Construction Certification 2 Planted model Planting eigenvalues Analysis Distinguishing
More informationPROJECTIVE NON-NEGATIVE MATRIX FACTORIZATION WITH APPLICATIONS TO FACIAL IMAGE PROCESSING
st Reading October 0, 200 8:4 WSPC/-IJPRAI SPI-J068 008 International Journal of Pattern Recognition and Artificial Intelligence Vol. 2, No. 8 (200) 0 c World Scientific Publishing Company PROJECTIVE NON-NEGATIVE
More informationLecture Note 5: Semidefinite Programming for Stability Analysis
ECE7850: Hybrid Systems:Theory and Applications Lecture Note 5: Semidefinite Programming for Stability Analysis Wei Zhang Assistant Professor Department of Electrical and Computer Engineering Ohio State
More informationCS675: Convex and Combinatorial Optimization Fall 2016 Combinatorial Problems as Linear and Convex Programs. Instructor: Shaddin Dughmi
CS675: Convex and Combinatorial Optimization Fall 2016 Combinatorial Problems as Linear and Convex Programs Instructor: Shaddin Dughmi Outline 1 Introduction 2 Shortest Path 3 Algorithms for Single-Source
More informationECS289: Scalable Machine Learning
ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Oct 11, 2016 Paper presentations and final project proposal Send me the names of your group member (2 or 3 students) before October 15 (this Friday)
More informationHandout 8: Dealing with Data Uncertainty
MFE 5100: Optimization 2015 16 First Term Handout 8: Dealing with Data Uncertainty Instructor: Anthony Man Cho So December 1, 2015 1 Introduction Conic linear programming CLP, and in particular, semidefinite
More informationLearning Spectral Clustering
Learning Spectral Clustering Francis R. Bach Computer Science University of California Berkeley, CA 94720 fbach@cs.berkeley.edu Michael I. Jordan Computer Science and Statistics University of California
More informationDOWNLINK transmit beamforming has recently received
4254 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 58, NO. 8, AUGUST 2010 A Dual Perspective on Separable Semidefinite Programming With Applications to Optimal Downlink Beamforming Yongwei Huang, Member,
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 information