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

Research Projects

Organizational Units

Journal Issue

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

Source

Journal of Machine Learning Research

Book Title

Entity type

Publication

Access Statement

License Rights

DOI

Restricted until