paper-with-me

홈 › Papers

Prediction with Corrupted Expert Advice

2020-02-24 · NeurIPS 2020 12 · Idan Amir, Idan Attias, Tomer Koren, Roi Livni, Yishay Mansour

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.

📄 PDF Abstract BibTeX arXiv:2002.10286

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Similar Papers 제목 키워드 기반

Advice-Efficient Prediction with Expert Advice

2013-04-12 · Yevgeny Seldin, Peter Bartlett, Koby Crammer

Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited …

Prediction

Fast rates for prediction with limited expert advice

2021-10-27 · NeurIPS 2021 12 · El Mehdi Saad, Gilles Blanchard

We investigate the problem of minimizing the excess generalization error with respect to the best expert prediction in a finite family in the stochastic setting, under limited access to information. We assume that the le…

Prediction

Optimal Tracking in Prediction with Expert Advice

2022-08-07 · Hakan Gokcesu, Suleyman S. Kozat

We study the prediction with expert advice setting, where the aim is to produce a decision by combining the decisions generated by a set of experts, e.g., independently running algorithms. We achieve the min-max optimal …

Decision MakingPrediction

On the asymptotic optimality of the comb strategy for prediction with expert advice

2019-02-06 · Erhan Bayraktar, Ibrahim Ekren, Yili Zhang

For the problem of prediction with expert advice in the adversarial setting with geometric stopping, we compute the exact leading order expansion for the long time behavior of the value function. Then, we use this expans…

Prediction with Advice of Unknown Number of Experts

2014-08-09 · Alexey Chernov, Vladimir Vovk

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge b…

Prediction