paper-with-me

Papers

Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs

2018-10-25 · NeurIPS 2018 12 · Han Shao, Xiaotian Yu, Irwin King, Michael R. Lyu

In linear stochastic bandits, it is commonly assumed that payoffs are with sub-Gaussian noises. In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0,1]$. We rigorously analyze the regret lower bound of LinBET as $\Omega(T^{\frac{1}{1+\epsilon}})$, implying that finite moments of order 2 (i.e., finite variances) yield the bound of $\Omega(\sqrt{T})$, with $T$ being the total number of rounds to play bandits. The provided lower bound also indicates that the state-of-the-art algorithms for LinBET are far from optimal. By adopting median of means with a well-designed allocation of decisions and truncation based on historical information, we develop two novel bandit algorithms, where the regret upper bounds match the lower bound up to polylogarithmic factors. To the best of our knowledge, we are the first to solve LinBET optimally in the sense of the polynomial order on $T$. Our proposed algorithms are evaluated based on synthetic datasets, and outperform the state-of-the-art results.

📄 PDF Abstract BibTeX arXiv:1810.10895

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Differentially Private Stochastic Linear Bandits: (Almost) for Free

2022-07-07 · Osama A. Hanna, Antonious M. Girgis, Christina Fragouli, Suhas Diggavi

In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal n…

Optimal Best-arm Identification in Linear Bandits

2020-06-29 · NeurIPS 2020 12 · Yassir Jedra, Alexandre Proutiere

We study the problem of best-arm identification with fixed confidence in stochastic linear bandits. The objective is to identify the best arm with a given level of certainty while minimizing the sampling budget. We devis…

Delayed Feedback in Generalised Linear Bandits Revisited

2022-07-21 · Benjamin Howson, Ciara Pike-Burke, Sarah Filippi

The stochastic generalised linear bandit is a well-understood model for sequential decision-making problems, with many algorithms achieving near-optimal regret guarantees under immediate feedback. However, the stringent …

Decision MakingSequential Decision Making

An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits

2016-05-27 · Peter Auer, Chao-Kai Chiang

We present an algorithm that achieves almost optimal pseudo-regret bounds against adversarial and stochastic bandits. Against adversarial bandits the pseudo-regret is $O(K\sqrt{n \log n})$ and against stochastic bandits …

Gamification of Pure Exploration for Linear Bandits

2020-07-02 · ICML 2020 1 · Rémy Degenne, Pierre Ménard, Xuedong Shang, Michal Valko

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the exi…

Experimental Design