pith. sign in

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount of corruption with virtually no degradation in performance.

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions

stat.ML · 2026-05-21 · unverdicted · novelty 7.0

In first-price auctions with feedback-only shilling, an algorithm combining robust interval elimination and optimistic debiasing with racing achieves near-optimal regret rates of O(T^{2/3}) or O(sqrt(T)) and matches a lower bound in the single-active-region case.

citing papers explorer

Showing 1 of 1 citing paper.

  • Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions stat.ML · 2026-05-21 · unverdicted · none · ref 7 · internal anchor

    In first-price auctions with feedback-only shilling, an algorithm combining robust interval elimination and optimistic debiasing with racing achieves near-optimal regret rates of O(T^{2/3}) or O(sqrt(T)) and matches a lower bound in the single-active-region case.