Prediction with Corrupted Expert Advice

NeurIPS 2020

Prediction with Corrupted Expert Advice

Dec 06, 2020
|
40 views
|
Details
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. Speakers: Idan Amir, Idan Attias, Tomer Koren, Roi Livni, Yishay Mansour

Comments
loading...