NeurIPS 2020spotlight46 citations

Prediction with Corrupted Expert Advice

Idan Amir, Idan Attias, Tomer Koren, Yishay Mansour, Roi Livni

Abstract

We revisit the fundamental problem of prediction with expert advice, in a setting where the environment is benign and generates losses stochastically, but the feedback observed by the learner is subject to a moderate adversarial corruption. We prove that a variant of the classical Multiplicative Weights algorithm with decreasing step sizes achieves constant regret in this setting and performs optimally in a wide range of environments, regardless of the magnitude of the injected corruption. Our results reveal a surprising disparity between the often comparable Follow the Regularized Leader (FTRL) and Online Mirror Descent (OMD) frameworks: we show that for experts in the corrupted stochastic regime, the regret performance of OMD is in fact strictly inferior to that of FTRL.

BibTeX
@inproceedings{NEURIPS2020_a5122944,
 author = {Amir, Idan and Attias, Idan and Koren, Tomer and Mansour, Yishay and Livni, Roi},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {14315--14325},
 publisher = {Curran Associates, Inc.},
 title = {Prediction with Corrupted Expert Advice},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/a512294422de868f8474d22344636f16-Paper.pdf},
 volume = {33},
 year = {2020}
}
Prediction with Corrupted Expert Advice · NeurIPS 2020