Efficient Online Learning via Randomized Rounding

Efficient Online Learning via Randomized Rounding

Cached

Download Links

by Nicolò Cesa-bianchi , Ohad Shamir

BibTeX

@MISC{Cesa-bianchi_efficientonline,
    author = {Nicolò Cesa-bianchi and Ohad Shamir},
    title = {Efficient Online Learning via Randomized Rounding},
    year = {}
}

Bookmark

OpenURL

Abstract

Most online algorithms used in machine learning today are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, which combines “random playout ” and randomized rounding of loss subgradients. As an application of our approach, we provide the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question linking batch learning and transductive online learning. 1

Citations

267	How to use expert advice - Cesa-Bianchi, Freund, et al. - 1997
185	Rademacher and gaussian complexities: Risk bounds and structural - Bartlett, Mendelson - 2002
90	T.S.: Maximum-margin matrix factorization - Srebro, Rennie, et al. - 2005
58	A.: Probabilistic matrix factorization - Salakhutdinov, Mnih - 2008
31	Collaborative filtering with temporal dynamics - Koren - 2009
23	Consistency of trace norm minimization - Bach - 2008
21	Separating distribution-free and mistake-bound learning models over the boolean domain - Blum - 1994
18	trace-norm and max-norm - Rank - 2005
15	Approximate methods for sequential decision making using expert advice - CHUNG - 1994
14	Optimal strategies and minimax lower bounds for online convex games - Abernethy, Bartlett, et al. - 2008
13	A stochastic view of optimal regret through minimax duality - Abernethy, Agarwal, et al.
10	The convex optimization approach to regret minimization. Optimization for - Hazan - 2012
9	Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm - Salakhutdinov, Srebro
6	Agnostic online learning - Ben-David, Pal, et al. - 2009
6	Practical Large-Scale Optimization for Max-Norm Regularization - Lee, Recht, et al.
5	Online learning: Random averages, combinatorial parameters, and learnability - Rakhlin, Sridharan, et al.
4	Online learning versus offline learning - Ben-David, Kushilevitz, et al. - 1997
4	Collaborative filtering with the trace norm - Shamir, Shalev-Shwartz - 2011
3	A Course on Empirical Processes, École de Probabilités de St. Flour - Dudley - 1982
3	From batch to transductive online learning - Kakade, Kalai - 2009
2	Repeated games against budgeted adversaries - Abernethy, Warmuth - 2010
2	Learning with the weighted trace-norm under arbitrary sampling distributions - Foygel, Salakhutdinov, et al.
1	9 Derivation of the Minimax Forecaster In this appendix, we outline how the Minimax Forecaster is derived, as well as its associated guarantees. This outline closely follows the exposition in [10, Chapter 8], to which we refer the reader for some of the t - Rank, COLT - 2005