Online and Distribution-Free Robustness: Regression and Contextual Bandits with Huber Contamination

Cited by: 1|Views8

Abstract:

In this work we revisit two classic high-dimensional online learning problems, namely regression and linear contextual bandits, from the perspective of adversarial robustness. Existing works in algorithmic robust statistics make strong distributional assumptions that ensure that the input data is evenly spread out or comes from a nice g...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments