Subgradient methods for maximum margin structured learning

Subgradient methods for maximum margin structured learning (2006)

Cached

by Nathan D. Ratliff , J. Andrew Bagnell , Martin A. Zinkevich

Venue:	In ICML Workshop on Learning in Structured Output Spaces
Citations:	15 - 0 self

BibTeX

@INPROCEEDINGS{Ratliff06subgradientmethods,
    author = {Nathan D. Ratliff and J. Andrew Bagnell and Martin A. Zinkevich},
    title = {Subgradient methods for maximum margin structured learning},
    booktitle = {In ICML Workshop on Learning in Structured Output Spaces},
    year = {2006}
}

Bookmark

OpenURL

Abstract

Maximum margin structured learning (MMSL) has recently gained recognition within the machine learning community as a tractable method for large scale learning. However, most current methods are limited

Citations

487	Gradient-based learning applied to document recognition - LeCun, Bottou, et al. - 1998
315	BMaximum-margin Markov networks - Taskar, Guestrin, et al. - 2003
208	Large margin methods for structured and interdependent output variables - Tsochantaridis, Joachims, et al.
192	Minimization Methods for Non-differentiable Functions - Shor - 1985
83	On the generalization ability of on-line learning algorithms - Cesa-Bianchi, Conconi, et al. - 2004
66	M.: Maximum margin planning - Ratliff, Bagnell, et al. - 2006
65	Logarithmic regret algorithms for online convex optimization - Hazan, Agarwal, et al. - 2006
33	Convergence rate of incremental subgradient algorithms,” in Stochastic Optimization: Algorithms and Applications - Nedić, Bertsekas - 2000
30	Solving large scale linear prediction problems using stochastic gradient descent algorithms - Zhang
22	Structured prediction via the extragradient method - Taskar, Lacoste-julien, et al. - 2005
1	Preliminary version in Proc. of the 14th conference on Neural Information processing Systems (NIPS - SearchDuame, Langford, et al. - 2001