Exponential family matrix completion under structural constraints

31st International Conference on Machine Learning, ICML 2014

Volumn 5, Issue , 2014, Pages 3964-3976

  Gunasekar, Suriya ^a   Ravikumar, Pradeep ^a   Ghosh, Joydeep ^a  

^a UNIVERSITY OF TEXAS AT AUSTIN   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; GAUSSIAN NOISE (ELECTRONIC); LEARNING SYSTEMS; UNCERTAINTY ANALYSIS;

ADDITIVE GAUSSIAN NOISE; EXPONENTIAL FAMILY; EXPONENTIAL FAMILY DISTRIBUTIONS; HETEROGENEOUS DATA; MATRIX COMPLETION PROBLEMS; STATISTICAL GUARANTEE; STRUCTURAL CONSTRAINTS; STRUCTURED MATRIXES;

MATRIX ALGEBRA;

EID: 84919816524     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (34)

1. Banerjee, A., Merugu, S., Dhillon, I. S., and Ghosh, J. Clustering with bregman divergences. JMLR, 6:1705-1749, 2005.
2. Candes, E. J. and Plan, Y. Matrix completion with noise. Proceedings of the IEEE, 2010.
3. Candes, E. J. and Recht, B. Exact matrix completion via convex optimization. Foundations of Computational mathematics, 2009.
4. Candes, E. J. and Tao, T. The power of convex relaxation: near-optimal matrix completion. IEEE Transactions on Information Theory, 2010.
5. Candes, E. J., Li, X., Ma, Y., and Wright, J. Robust principal component analysis? Journal of the ACM (JACM), 58(3):11, 2011.
6. Collins, M., Dasgupta, S., and Schapire, R. E. A generalization of principal components analysis to the exponential family. In NIPS, pp. 617-624, 2001.
7. Davenport, M. A., Plan, Y., Berg, E., and Wootters, M. 1-bit matrix completion. arXiv preprint arXiv: 1209.3672, 2012.
8. Fazel, M., Hindi, H, and Boyd, S. P. A rank minimization heuristic with application to minimum order system approximation. In American Control Conference, pp. 4734-1739, 2001.
9. Forster, J. and Warmuth, M. Relative expected instantaneous loss bounds. Journal of Computer and System Sciences, 2002.
10. Gordon, G. J. Generalized" 2 linear" 2 models. In NIPS, pp. 577-584, 2002.
11. Jain, P., Netrapalli, P., and Sanghavi, S. Low-rank matrix completion using alternating minimization. In STOC, 2013.
12. Kakade, S. M., Shamir, O., Sridharan, K., and Tewari, A. Learning exponential families in high-dimensions: Strong convexity and sparsity. In AISTATS, JMLR Workshop and Conference Proceedings, pp. 381-388, 2010.
13. Keshavan, R. H., Montanari, A., and Oh, S. Matrix completion from a few entries. IEEE Transactions on Information Theory, 2010a.
14. Keshavan, R. H., Montanari, A., and Oh, S. Matrix completion from noisy entries. JMLR, 2010b.
15. Laurent, M. Matrix completion problems. Encyclopedia of Optimization, 3:221-229, 2009.
16. Ledoux, M. and Talagrand, M. Probability in Ba-nach Spaces: isoperimetry and processes, volume 23. Springer, 1991.
17. Mnih, A. and Salakhutdinov, R. Probabilistic matrix factorization. In MPS, pp. 1257-1264, 2007.
18. Mohamed, S., Ghahramani, Z., and Heller, K. A. Bayesian exponential family pea. In MPS, pp. 1089-1096, 2008.
19. Negahban, S. Structured Estimation in High-Dimensions. PhD thesis, EECS Department, University of California, Berkeley, May 2012.
20. Negahban, S. and Wainwright, M. J. Joint support recovery under high-dimensional scaling: Benefits and perils of 11,-regularization. MPS, 21:1161-1168, 2008.
21. Negahban, S. and Wainwright, M. J. Restricted strong convexity and weighted matrix completion: Optimal bounds with noise. The Journal of Machine Learning Research, 98888:1665-1697,2012.
22. Obozinski, G., Wainwright, M. J., and Jordan, M. I. Support union recovery in high-dimensional multivariate regression. The Annals of Statistics, 39(1): 1-47, 2011.
23. Recht, B. A simpler approach to matrix completion. JMLR, 12:3413-3430, 2011.
24. Salakhutdinov, R. and Mnih, A. Bayesian probabilistic matrix factorization using markov chain monte carlo. In ICML, pp. 880-887. ACM, 2008.
25. Srebro, N., Rennie, J., and Jaakkola, T. S. Maximum-margin matrix factorization. In MPS, pp. 1329-1336, 2004.
26. Tipping, M. E. and Bishop, C. M. Probabilistic principal component analysis. Journal of the Royal Statistical Society: Series B (Statistical Methodology), pp. 611-622, 1999.
27. Vershynin, R. Introduction to the non-asymptotic analysis of random matrices. arXiv preprint arXiv.1011.3027, 2010.
28. Yang, E. and Ravikumar, P. Dirty statistical models. In MPS, 2013.
29. Yang, E., Allen, G., Liu, Z., and Ravikumar, P. Graphical models via generalized linear models. In MPS, 2012.
30. Yang, E., Ravikumar, P., Allen, G. I., and Liu, Z. Conditional random fields via univariate exponential families. In Advances in Neural Information Processing Systems, pp. 683-691,2013.
31. Ahlswede, R. and Winter, A. Strong converse for identification via quantum channels. IEEE Transactions on Information Theory, 48 (3): 569-579, 2002.
32. Ledoux M., Talagrand M. Probability in Banach Spaces: isoperimetry and processes, volume 23. Springer, 1991.
33. Raskutti G., Wainwright M. J, Yu B. Restricted eigenvalue properties for correlated gaussian designs. The Journal of Machine Learning Research, 99: 2241-2259, 2010.
34. Vershynin R. A note on sums of independent random matrices after ahlswede-winter. Lecture Notes, 2009.