Algorithms and hardness for robust subspace recovery

Journal of Machine Learning Research

Volumn 30, Issue , 2013, Pages 354-375

  Hardt, Moritz ^a   Moitra, Ankur ^b  

^a IBM ALMADEN RESEARCH CENTER   (United States)

^b INSTITUTE FOR ADVANCED STUDY   (United States)

Author keywords

Principal component analysis; Robust statistics; Subspace recovery; Unique games conjecture

Indexed keywords

COMPUTER SCIENCE; ESTIMATION; MATRIX ALGEBRA; PRINCIPAL COMPONENT ANALYSIS; RECOVERY; STATISTICS; UNSUPERVISED LEARNING;

HIGH DIMENSIONS; MATROID THEORY; ROBUST STATISTICS; SMALL-SET EXPANSIONS; SUBSPACE RECOVERIES; UNIQUE GAMES CONJECTURE;

ALGORITHMS;

EID: 84897101907     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (38)

1. F. Barthe. On a reverse form of the Brascamp-Lieb inequality. Invent. Math., 134(2): 335-361, 1998.
2. H. J. Brascamp and E. H. Lieb. Best constants in Young's inequality, its converse, and its generalization to more than three functions. Advances in Math., 20(2): 151-173, 1976.
3. E. Candes and B. Recht. Exact matrix completion via convex optimization. Foundations of Comp. Math., pages 717-772, 2009.
4. E. Candes, X. Li, Y. Ma, and J. Wright. Robust principal component analysis? Journal of the ACM, 2011.
5. E. Carlen and D. Cordero-Erausquin. Subadditivity of the entropy and its relation to brascamp-lieb type inequalities. Geometric and Functional Analysis, 19(2): 373-405, 2009.
6. N and related entropy inequalities. J. Geom. Anal., 14(3): 487-520, 2004.
7. V. Chandrasekaran, S. Sanghavi, P. Parrilo, and A. Willsky. Rank-sparsity incoherence for matrix decomposition. SIAM J. Optim., pages 572-596, 2011.
8. W. Cunningham. Testing membership in matroid polyhedra. J. Combin. Theory Ser. B, pages 161-188, 1984.
9. A. Deshpande, M. Tulsiani, and N. Vishnoi. Algorithms and hardness for subspace approximation. SODA, pages 482-496, 2011.
10. D. Donoho and P. Huber. The notion of breakdown point. A Festshrift for Erich L. Lehmann, pages 157-184, 1983.
11. J. Dunagan and S. Vempala. Optimal outlier removal in high-dimensional spaces. J. Comput. Syst. Sci., pages 335-373, 2000.
12. H. Edelsbrunner and D. Souvaine. Computing median-of-squares regression lines and guided topological sweep. Journal of the Amer. Stat. Assoc., pages 115-119, 1990.
13. J. Edmonds. Submodular functions, matroids, and certain polyhedra. In Combinatorial Structures, pages 69-87. 1970.
14. M. Fischler and R. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, pages 381-395, 1981.
15. M. Grótschel, L. Lovász, and A. Schrijver. The ellipsoid method and its consequences in combinatorial optimization. Combinatorica, pages 169-197, 1981.
16. V. Guruswami and P. Raghavendra. Hardness of solving sparse overdetermined linear systems: A. pages 1-20, 2009. 3-query PCP over integers. ACM Trans. Comput. Theory.
17. V. Guruswami, P. Raghavendra, R. Saket, and Y. Wu. Bypassing UGC for some optimal geometric inapproximability results. SODA, pages 699-717, 2012.
18. P. Huber. Robust Statistics. 1981. John Wiley & Sons.
19. S. Iwata, L. Fleischer, and S. Fujishige. A combinatorial strongly polynomial time algorithm for minimizing submodular functions. JACM, pages 761-777, 2001.
20. V. Kabanets and R. Impagliazzo. Constructive proofs of concentration bounds. APPROX-RANDOM, pages 617-631, 2010.
21. L. Khachiyan. On the complexity of approximating extremal determinants in matrices. Journal of Complexity, pages 138-153, 1995.
22. S. Khot and D. Moshkovitz. Hardness of approximately solving linear equations over the reals. STOC, pages 413-420, 2011.
23. P. Lax. Linear algebra. 2007. Wiley Interscience.
24. G. Lerman, M. McCoy, J. Tropp, and T. Zhang. Robust computation of linear models, or how to find a needle in a haystack. Arxiv, 2012.
25. J. Matousek. Lectures on Discrete Geometry. 2002. Springer-Verlag New York, Inc.
26. A. Naor, O. Regev, and T. Vidick. Efficient rounding for the noncommutative grothendieck inequality. STOC, 2013.
27. A. Nemirovski. Lectures on modern convex optimization. 2005. http://www2.isye.gatech.edu/~nemirovs/.
28. P. Raghavendra and D. Steurer. Graph expansion and the unique games conjecture. STOC, pages 755-764, 2010.
29. P. Raghavendra, D. Steurer, and M. Tulsiani. Reductions between expansion problems. Electronic Colloquium on Computational Complexity (ECCC), 2010. 17: 172.
30. B. Recht, M. Fazel, and P. Parrilo. Guaranteed minimum rank solutions of matrix equations via nuclear norm minimization. SIAM Rev., pages 471-501, 2010.
31. P. Rousseeuw. Least median squares regression. Journal of the Amer. Stat. Assoc., pages 871-880, 1984.
32. P. Rousseeuw and A. Leroy. Robust Regression and Outlier Detection. 1987. John Wiley & Sons.
33. A. Schrijver. A combinatorial algorithm for minimizing submodular functions in strongly polynomial time. J. Combin. Theory Ser. B, pages 346-355, 2000.
34. M. Soltanolkotabi and E. Candes. A geometric analysis of subspace clustering with outliers. Ann. of Stat., pages 2195-2238, 2012.
35. S. Vempala. The joy of PCA. 2010. http://www.cc.gatech.edu/events/cse- seminar-santosh-vempala-0.
36. H. Xu, C. Carmanis, and S. Sanghavi. Robust PCA via outlier pursuit. IEEE Trans. Inform. Theory, pages 1-24, 2010.
37. H. Xu, C. Caramanis, and S. Mannor. Outlier-robust PCA: The high-dimensional case. IEEE Transactions on Information Theory, 59(1): 546-572, 2013.
38. T. Zhang and G. Lerman. A novel m-estimator for robust pca. Arxiv, 2011.