Robust Probabilistic Inference

Yishay Mansour, Aviad Rubinstein, Moshe Tennenholtz

Abstract

Robust probabilistic inference is an extension of probabilistic inference, where some of the observations are adversarially corrupted. We model it as a zero-sum game between the adversary, who can select a modification rule, and the predictor, who wants to accurately predict the state of nature. Given a black-box access to a Bayesian inference in the classic (adversary-free) setting, our near optimal policy runs in polynomial time in the number of observations and the number of possible modification rules.
BibTeX
@inproceedings{mansour2015robust,
  author = {Yishay Mansour and Aviad Rubinstein and Moshe Tennenholtz},
  title = {{Robust Probabilistic Inference}},
  booktitle = {SODA},
  year = {2015},
  doi = {10.1137/1.9781611973730.31},
}

Loading related content...

Figure