On the interaction between norm and dimensionality: Multiple regimes in learning

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 647-654

  Liang, Percy ^a   Srebro, Nati ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ASYMPTOTICS; CLASSICAL PROBLEMS; GENERALIZATION ERROR; HIGH-DIMENSIONAL; LEARNING CURVES; LEARNING PROBLEM; LEARNING THEORY; MEASURES OF COMPLEXITY; PROBLEM COMPLEXITY;

LEARNING SYSTEMS;

ASYMPTOTIC ANALYSIS;

EID: 77956555966     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Bartiett, P. L. and Mendelson, S. Rademacher and Gaussian complexities: Risk bounds and structural results. In Computational Learning Theory, pp. 224-240, 2001.
2. Cesa-Bianchi, N. and Lugosi, G. Prediction, learning, and games. Cambridge University Press, Cambridge, UK, 2006.
3. Haussler, D., Kearns, M., Seung, H. S., and Tishby, N. Rigorous learning curve bounds from statistical mechanics. In Computational Learning Theory, pp. 76-87, 1994.
4. Liang, P., Bach, F., Bouchard, G., and Jordan, M. I. Asymptotically optimal regularization in smooth parametric models. In Advances in Neural Information Processing Systems (NIPS), Cambridge, MA, 2010. MIT Press.
5. Pollard, D. Convergence of Stochastic Processes. Springer-Verlag, 1984.
6. Shalev-Shwartz, S. Online Learning: Theory, Algorithms, and Applications. PhD thesis, The Hebrew University of Jerusalem, 2007.
7. Srebro, N., Sridharan, K., and Tewari, A. Stochastic optimization and online learning with smooth loss functions. Technical report, TTI Chicago, 2010.
8. van der Vaart, A. W. Asymptotic Statistics. Cambridge University Press, Cambridge, UK, 1998.
9. 1-constrained quadratic programming (lasso). IEEE Transactions on Information Theory, 55:2183-2202, 2009.