Linear regression under fixed-rank constraints: A Riemannian approach

Proceedings of the 28th International Conference on Machine Learning, ICML 2011

Volumn , Issue , 2011, Pages 545-552

  Meyer, Gilles ^a   Bonnabel, Silvère ^b   Sepulchre, Rodolphe ^a  

^a UNIVERSITY OF LIÈGE   (Belgium)

^b PSL RESEARCH UNIVERSITY   (France)

Author keywords

[No Author keywords available]

Indexed keywords

HIGH-DIMENSIONAL PROBLEMS; LINE SEARCH ALGORITHM; LINEAR REGRESSION MODELS; LOCAL CONVERGENCE; MATRIX; NUMERICAL EXPERIMENTS; RIEMANNIAN MANIFOLD;

CONSTRAINED OPTIMIZATION; GEOMETRY; LEARNING SYSTEMS; LINEAR REGRESSION; MATRIX ALGEBRA;

LEARNING ALGORITHMS;

EID: 80053443288     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. Abernethy, J., Bach, F., Evgeniou, T., and Vert, J.-P. A new approach to collaborative filtering: Operator estimation with spectral regularization. Journal of Machine Learning Research, 10(Mar):803-826, 2009.
2. Absil, P.-A., Mahony, R., and Sepulchre, R. Optimization Algorithms on Matrix Manifolds. Princeton University Press, 2008.
3. Amit, Y., Fink, M., Srebro, N., and Ullman, S. Uncovering shared structures in multiclass classification. In Proceedings of the 24th International Conference on Machine Learning (ICML), 2007.
4. Bach, F. Consistency of trace norm minimization. Journal of Machine Learning Research, 9(Jun):1019-1048, 2008.
5. Balzano, L., Nowak, R., and Recht, B. Online identification and tracking of subspaces from highly incomplete information. arXiv:1006.4046v1, 2010.
6. Bleakley, K. and Yamanishi, Y. Supervised prediction of drug-target interactions using bipartite local models. Bioinformatics, 25(18):2397-2403, 2009.
7. Cai, D., He, X., and Han, J. Efficient kernel discriminant analysis via spectral regression. IEEE International Conference on Data Mining (ICDM), 2007.
8. Cai, J.-F., Candes, E. J., and Shen, Z. A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization, 20(4):1956-1982, 2008.
9. Daniel, J., Gragg, W.B., Kaufman, L., and Stewart, G. W. Reorthogonalization and stable algorithms for updating the Gram-Schmidt QR factorization. Math. Comp., 30:772-795, 1976.
10. Evgeniou, T., Micchelli, C.A., and Pontil, M. Learning multiple tasks with kernel methods. Journal of Machine Learning Research, 6(Apr):615-637, 2005.
11. Fazel, M. Matrix rank minimization with applications. PhD thesis, Stanford University, 2002.
12. Helmke, U. and Moore, J. Optimization and Dynamical Systems. Springer, 1996.
13. Jain, P., Meka, R., and Dhillon, I. Guaranteed rank minimization via singular value projection. In Advances in Neural Information Processing Systems (NIPS), 2010.
14. Keshavan, R., Montanari, A., and Oh, S. Matrix completion from noisy entries. Journal of Machine Learning Research, 11(Jul):2057-2078, 2010.
15. Lee, K. and Bresler, Y. Admira: Atomic decomposition for minimum rank approximation. IEEE Trans. on Information Theory, 56(9):4402-4416, 2010.
16. Meyer, G., Bonnabel, S., and Sepulchre, R. Regression on fixed-rank positive semidefinite matrices: a Riemannian approach. Journal of Machine Learning Research, 12(Feb):593-625, 2011.
17. Nocedal, J. and Wright, S. J. Numerical Optimization, Second Edition. Springer, 2006.
18. Recht, B., Fazel, M., and Parrilo, P. A. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Review, 53(3):471-501, August 2010.
19. Rennie, J. and Srebro, N. Fast maximum margin matrix factorization for collaborative prediction. In Proceedings of the 22nd International Conference on Machine Learning (ICML), 2005.
20. Shalit, U., Weinshall, D., and Chechik, G. Online learning in the manifold of low-rank matrices. In Advances in Neural Information Processing Systems (NIPS), 2010.
21. Simonsson, L. and Eldén, L. Grassmann algorithms for low rank approximation of matrices with missing values. BIT Numerical Math., 50(1):173-191, 2010.