Variable Metric Stochastic Approximation Theory

[edit]

Peter Sunehag, Jochen Trumpf, S.V.N. Vishwanathan, Nicol Schraudolph ;
Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, PMLR 5:560-566, 2009.

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 in the areas of elicitation of properties of distributions using prediction markets and in learning from expert advice.

Related Material