NeurIPS 2018poster141 citations
Differentially Private Contextual Linear Bandits
Abstract
We study the contextual linear bandit problem, a version of the standard stochastic multi-armed bandit (MAB) problem where a learner sequentially selects actions to maximize a reward which depends also on a user provided per-round context. Though the context is chosen arbitrarily or adversarially, the reward is assumed to be a stochastic function of a feature vector that encodes the context and selected action. Our goal is to devise private learners for the contextual linear bandit problem.
BibTeX
@inproceedings{NEURIPS2018_a1d7311f,
author = {Shariff, Roshan and Sheffet, Or},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Differentially Private Contextual Linear Bandits},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/a1d7311f2a312426d710e1c617fcbc8c-Paper.pdf},
volume = {31},
year = {2018}
}