In the paper we consider one point and two point multiarmed bamdit problems. In other words we consider the online stochastic convex optimization problems with oracle that return the value (realization) of the function at one point or at two points. We allow these values to be inexact, but the level of noise should be small enough. We generalize well known results for inexact oracle case. And we also generalize classical results to prox-structures differ from euclidian.
@article{arxiv.1509.01679,
title = {Nonlinear stochastic multiarmed bandit problems with inexact oracle},
author = {Alexander Gasnikov and Ekaterina Krymova and Anastasia Lagunovskaya and Ilnura Usmanova and Fedor Fedorenko},
journal= {arXiv preprint arXiv:1509.01679},
year = {2017}
}
Comments
12 pages, in Russia, Avtomatika i Telemekhanika. 2017