paper-with-me

홈 › Papers

The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits

2023-09-06 · Sepehr Assadi, Chen Wang

We give a near-optimal sample-pass trade-off for pure exploration in multi-armed bandits (MABs) via multi-pass streaming algorithms: any streaming algorithm with sublinear memory that uses the optimal sample complexity of $O(\frac{n}{\Delta^2})$ requires $\Omega(\frac{\log{(1/\Delta)}}{\log\log{(1/\Delta)}})$ passes. Here, $n$ is the number of arms and $\Delta$ is the reward gap between the best and the second-best arms. Our result matches the $O(\log(\frac{1}{\Delta}))$-pass algorithm of Jin et al. [ICML'21] (up to lower order terms) that only uses $O(1)$ memory and answers an open question posed by Assadi and Wang [STOC'20].

📄 PDF Abstract BibTeX arXiv:2309.03145

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Nearly Tight Bounds for Exploration in Streaming Multi-armed Bandits with Known Optimality Gap

2025-02-03 · Nikolai Karpov, Chen Wang

We investigate the sample-memory-pass trade-offs for pure exploration in multi-pass streaming multi-armed bandits (MABs) with the *a priori* knowledge of the optimality gap $\Delta_{[2]}$. Here, and throughout, the optim…

Multi-Armed 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

Fast OBDD Reordering using Neural Message Passing on Hypergraph

2018-11-06 · Feifan Xu, Fei He, Enze Xie, Liang Li

Ordered binary decision diagrams (OBDDs) are an efficient data structure for representing and manipulating Boolean formulas. With respect to different variable orders, the OBDDs' sizes may vary from linear to exponential…

Optimal Streaming Algorithms for Multi-Armed Bandits

2024-10-23 · Tianyuan Jin, Keke Huang, Jing Tang, Xiaokui Xiao

This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of $n$ arms with reward distributions supported on $[0,1]$ with unknown means. The arms in th…

Multi-Armed Bandits

HOTA: Hamiltonian framework for Optimal Transport Advection

2025-07-23 · Nazar Buzun, Daniil Shlenskii, Maxim Bobrin, Dmitry V. Dylov arxiv

Optimal transport (OT) has become a natural framework for guiding the probability flows. Yet, the majority of recent generative models assume trivial geometry (e.g., Euclidean) and rely on strong density-estimation assum…