Winnowing subspaces

ACM International Conference Proceeding Series

Volumn 227, Issue , 2007, Pages 999-1006

  Warmuth, Manfred K ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; MATRIX ALGEBRA; ONLINE SYSTEMS;

DISJUNCTIONS; MATRIX EXPONENTIATED GRADIENT ALGORITHM; PROJECTION MATRIX; WINNOWING SUBSPACES;

LEARNING SYSTEMS;

EID: 34547986383     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/1273496.1273622     Document Type: Conference Paper

References (17)

1. Arora, S., & Kale, S. (2007). A combinatorial primaldual approach to semidefinite programs. Proc. 39th Annual ACM Symposium on Theory of Computing. ACM. To appear.
2. Auer, P., & Warmuth, M. K. (1998). Tracking the best disjunction. Machine Learning, 32, 127-150. Earlier version in 36th FOCS, 1995.
3. Bhatia, R. (1997). Matrix analysis. Berlin: Springer.
4. Cesa-Bianchi, N., & Gentile, C. (2006). Improved risk tail bounds for on-line learning. Advances in Neural Information Processing Systems 18 (NIPS 05). MIT Press.
5. Floyd, S., & Warmuth, M. (1995). Sample compression, learnability, and the Vapnik-Chervonenkis dimension. Machine Learning, 21, 269-304.
6. Gentile, C., & Warmuth, M. K. (1998). Hinge loss and average margin. In Advances in Neural Information Processing Systems 11 (NIPS*98).
7. Golub, G. H., & Loan, C. F. V. (1996). Matrix computations (third edition). The John Hopkins University Press.
8. Herbster, M., & Warmuth, M. K. (2001). Tracking the best linear predictor. Journal of Machine. Learning Research, 1, 281-309.
9. Kivinen, J., & Warmuth, M. K. (1997). Additive versus exponentiated gradient updates for linear prediction. Information and Computation, 132, 1-64.
10. Kuzmin, D., & Warmuth, M. K. (2007). Online Kernel PCA with entropie matrix updates. ICML '07: Proceedings of the 24rd international conference on Machine learning. Corvallis, Oregon: ACM Press.
11. Littlestone, N. (1988). Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2, 285-318.
12. Littlestone, N. (1989). From on-line to batch learning. Proceedings of the Second Annual Workshop on Computational Learning Theory (pp. 269-284). San Mateo, CA: Morgan Kaufmann.
13. Nielsen, M., & Chuang, I. (2000). Quantum computation and quantum information. Cambridge University Press.
14. Tsuda, K., Rätsch, G., & Warmuth, M. K. (2005). Matrix exponentiated gradient updates for on-line learning and Bregman projections. Journal of Machine Learning Research, 6, 995-1018.
15. Warmuth, M. K. (2007). When is there a free matrix lunch. Proc. of the 20th Annual Conference on Learning Theory (COLT 07). San Diego, CA: Springer. Open problem, to appear.
16. Warmuth, M. K., & Kuzmin, D. (2006a). Online variance minimization. Proceedings of the 19th Annual Conference on Learning Theory (COLT 06). Pittsburg: Springer.
17. Warmuth, M. K., & Kuzmin, D. (2006b). Randomized PCA algorithms with regret bounds that are logarithmic in the dimension. Advances in Neural Information Processing Systems 19 (NIPS 06). MIT Press.