Variable metric stochastic approximation theory
Date
Authors
Sunehag, Peter
Trumpf, Jochen
Vishwanathan, S. V.N.
Schraudolph, Nicol N.
Journal Title
Journal ISSN
Volume Title
Publisher
Access Statement
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
Keywords
Citation
Collections
Source
Journal of Machine Learning Research
Type
Book Title
Entity type
Publication