Variable Metric Stochastic Approximation Theory
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.
Cite
Text
Sunehag et al. "Variable Metric Stochastic Approximation Theory." Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009.Markdown
[Sunehag et al. "Variable Metric Stochastic Approximation Theory." Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009.](https://mlanthology.org/aistats/2009/sunehag2009aistats-variable/)BibTeX
@inproceedings{sunehag2009aistats-variable,
title = {{Variable Metric Stochastic Approximation Theory}},
author = {Sunehag, Peter and Trumpf, Jochen and Vishwanathan, S.V.N. and Schraudolph, Nicol},
booktitle = {Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics},
year = {2009},
pages = {560-566},
volume = {5},
url = {https://mlanthology.org/aistats/2009/sunehag2009aistats-variable/}
}