Skip navigation
Skip navigation

Variable Metric Stochastic Approximation Theory

Sunehag, Peter; Trumpf, Jochen; Vishwanathan, S.V.N.; Schraudolph, Nic


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.

CollectionsANU Research Publications
Date published: 2009
Type: Conference paper
Source: Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS 2009)


There are no files associated with this item.

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator