Prediction with Corrupted Expert Advice

NIPS 2020, 2020.

Cited by: 0|Views11
EI
Weibo:
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

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 size...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments