Variable Metric Stochastic Approximation Theory
Date
Authors
Sunehag, Peter
Trumpf, Jochen
Vishwanathan, S.V.N.
Schraudolph, Nic
Journal Title
Journal ISSN
Volume Title
Publisher
Society for Artificial Intelligence and Statistics
Abstract
We provide a variable metric stochastic approximation theory. In doing so, we provide a convergence theory for a large class of online variable metric methods including the recently introduced online versions of the BFGS algorithm and its limited-memory LBFGS variant. We also discuss the implications of our results for learning from expert advice.
Description
Citation
Collections
Source
Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS 2009)