Square deal: Lower bounds and improved relaxations for tensor recovery

31st International Conference on Machine Learning, ICML 2014

Volumn 2, Issue , 2014, Pages 1242-1250

  Mu, Cun ^a   Huang, Bo ^a   Wright, John ^b   Goldfarb, Donald ^a  

^a Och Spine at New York Presbyterian Hospitals   (United States)

^b Department of Electrical Engineering Columbia University ^*  (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING SYSTEMS; RECOVERY; RELAXATION PROCESSES; SIGNAL PROCESSING;

CONVEX RELAXATION; GAUSSIAN MEASUREMENTS; INCOMPLETE INFORMATION; LOWER BOUNDS; MULTIPLE STRUCTURES; SAMPLE COMPLEXITY; SUBOPTIMALITY; TENSOR RECOVERIES;

TENSORS;

EID: 84919948669     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (39)

1. Amelunxen, D., Lotz, M., McCoy, M., and Tropp, J. Living on the edge: A geometric theory of phase transitions in convex coptimization. arXivpreprint arXiv: 1303.6672, 2013.
2. Anandkumar, A., Ge, R., Hsu, D., Kakade, S., and Telgarsky, M. Tensor decompositions for learning latent variable models. arXiv preprint arXiv: 1210.7559, 2012.
3. Bayati, Mohsen, Lelarge, Marc, and Montanari, Andrea. Universality in polytope phase transitions and message passing algorithms. arXiv preprint arXiv: 1207.7321, 2012.
4. Candes, E., Romberg, J., and Tao, T. Stable signal recovery from incomplete and inaccurate measurements. Communications on Pure and Applied Mathematics, 59(8), 2006.
5. Chandrasekaran, V., Recht, B., Parrilo, P., and Willsky, A. The convex geometry of linear inverse problems. Foundations of Computational Mathematics, 12(6):805-849, 2012.
6. Cohen, S. B. and Collins, M. Tensor decomposition for fast latent- variable PCFG parsing. In NIPS, 2012.
7. Donoho, D. Compressed sensing. IEEE Trans. Info. Theory, 52 (4):1289-1306, 2006.
8. Ely, G., Aeron, S., Hao, N., and Kilmer, M. E. 5d and 4d pre- stack seismic data completion using tensor nuclear norm (tnn). preprint, 2013.
9. Fazel, M. Matrix rank minimization with applications. PhD thesis, Stanford University, 2002.
10. Gandy, S., Recht, B., and Yamada, I. Tensor completion and low- n-rank tensor recovery via convex optimization. Inverse Problems, 27(2):025010, 2011.
11. Goldfarb, D. and Qin, Z. Robust low-rank tensor recovery: Models and algorithms. SIAM Journal on Matrix Analysis and Applications, 35(1):225-253, 2014.
12. Gross, D. Recovering low-rank matrices from few coefficients in any basis. IEEE Trans. Info. Theory, 57(3): 1548-1566, 2011.
13. Hillar, C. and Lim, L. Most tensor problems are np-hard. Journal of the ACM (JACM), 60(6):45, 2013.
14. Huang, B., Ma, S., and Goldfarb, D. Accelerated linearized breg- man method. Journal of Scientific Computing, 54(2-3) :428- 453, 2013.
15. Huang, B., Mu, C., Goldfarb, D., and Wright, J. Provable low- rank tensor recovery, preprint, 2014.
16. Jaggi, M. Revisiting frank-wolfe: Projection-free sparse convex optimization. In ICML, 2013.
17. Kolda, T. and Bader, B. Tensor decompositions and applications. SIAM Review, 51(3):455-500, 2009.
18. Kreimer, N., Stanton, A. and Sacchi, M. D. Nuclear norm minimization and tensor completion in exploration seismology. In ICASSP, 2013.
19. Li, N. and Li, B. Tensor completion for on-board compression of hyperspectral images. In ICIP, 2010.
20. Li, Y., Yan, J., Zhou, Y., and Yang, J. Optimum subspace learning and error correction for tensors. In ECCV, 2010.
21. Liang, X., Ren, X., Zhang, Z., and Ma, Y. Repairing sparse low- rank texture. In ECCV 2012, 2012.
22. Lim, D., McFee, B., and Lanckriet, G. Robust structural metric learning. In ICML, 2013.
23. Lin, Z., Chen, M., and Ma, Y. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. arXiv preprint arXiv:1009.5055, 2010.
24. Liu, J., Musialski, P., Wonka, P., and Ye, J. Tensor completion for estimating missing values in visual data. In ICCV, 2009.
25. McCoy, M. A geometric analysis of convex demixing. PhD thesis, California Institute of Technology, 2013.
26. Mesgarani, N., Slaney, M., and Shamma, S.A. Discrimination of speech from nonspeech based on multiscale spectro-temporal modulations. IEEE Trans. Audio, Speech, and Language Pro-cessing, 14(3):920-930, 2006.
27. Negahban, S., Ravikumar, P., Wainwright, M., and Yu, B. A unified framework for high-dimensional analysis of m-estimators with decomposable regularizes. Stat. Sci., 27(4):528-557, 2012.
28. Nion, D. and Sidiropoulos, N. Tensor algebra and multidimensional harmonic retrieval in signal processing for mimo radar. IEEE Trans, on Signal Processing, 58(11):5693-5705, 2010.
29. Oymak, S., Jalali, A., Fazel, M., Eldar, Y., and Hassibi, B. Simultaneously structured models with application to sparse and low-rank matrices. arXiv preprint arXiv: 1212.3753, 2012.
30. Recht, B., Fazel, M., and Parrilo, P. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM review, 52(3):471-501, 2010.
31. Richard, E., Bach, F., and Vert, J. Intersecting singularities for multi-structured estimation. In ICML, 2013.
32. Romera-Paredes, B. and Pontil, M. A new convex relaxation for tensor completion. In NIPS, 2013.
33. Romera-Paredes, B., Aung, H., Bianchi-Berthouze, N., and Pontil, M. Multilinear multitask learning. In ICML, 2013.
34. Semerci, O., Hao, N., Kilmer, M., and Miller, E. Tensor-based formulation and nuclear norm regularization for multi-energy computed tomography. arXiv preprint arXiv: 1307.5348, 2013.
35. Signoretto, M., De Lathauwer, L., and Suykens, J. Nuclear norms for tensors and their use for convex multilinear estimation. Submitted to Linear Algebra and Its Applications, 43, 2010.
36. Signoretto, M., Tran Dinh, Q., Lathauwer, L., and Suykens, J. Learning with tensors: A framework based on convex optimization and spectral regularization. Machine Learning, pp. 1-49, 2013.
37. Tomioka, R., Suzuki, T., Hayashi, K., and Kashima, H. Statistical performance of convex tensor decomposition. In NIPS, 2011.
38. Tucker, L. Some mathematical notes on three-mode factor analysis. Psychometrika, 31(3):279-311, 1966.
39. Xu, Y, Hao, R., Yin, W and Su, Z. Parallel matrix factorization for low-rank tensor completion. arXiv preprint arXiv:1312.1254, 2013.