Prediction with Corrupted Expert Advice

Cited by: 1|Views35

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 si...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments