paper-with-me

Papers

Parallelizing Thompson Sampling

2021-06-02 · NeurIPS 2021 12 · Amin Karbasi, Vahab Mirrokni, Mohammad Shadravan

How can we make use of information parallelism in online decision making problems while efficiently balancing the exploration-exploitation trade-off? In this paper, we introduce a batch Thompson Sampling framework for two canonical online decision making problems, namely, stochastic multi-arm bandit and linear contextual bandit with finitely many arms. Over a time horizon $T$, our \textit{batch} Thompson Sampling policy achieves the same (asymptotic) regret bound of a fully sequential one while carrying out only $O(\log T)$ batch queries. To achieve this exponential reduction, i.e., reducing the number of interactions from $T$ to $O(\log T)$, our batch policy dynamically determines the duration of each batch in order to balance the exploration-exploitation trade-off. We also demonstrate experimentally that dynamic batch allocation dramatically outperforms natural baselines such as static batch allocations.

📄 PDF Abstract BibTeX arXiv:2106.01420

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingThompson Sampling

Similar Papers 제목 키워드 기반

Thompson sampling with the online bootstrap

2014-10-15 · Dean Eckles, Maurits Kaptein

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal…

Thompson Sampling

Asymptotic Convergence of Thompson Sampling

2020-11-08 · Cem Kalkanli, Ayfer Ozgur

Thompson sampling has been shown to be an effective policy across a variety of online learning tasks. Many works have analyzed the finite time performance of Thompson sampling, and proved that it achieves a sub-linear re…

Multi-Armed BanditsThompson Sampling

Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors

2017-08-16 · ICML 2018 7 · Yichi Zhou, Jun Zhu, Jingwei Zhuo

Thompson sampling has impressive empirical performance for many multi-armed bandit problems. But current algorithms for Thompson sampling only work for the case of conjugate priors since these algorithms require to infer…

Thompson Sampling

Distributed Thompson Sampling

2020-12-03 · Jing Dong, Tan Li, Shaolei Ren, Linqi Song

We study a cooperative multi-agent multi-armed bandits with M agents and K arms. The goal of the agents is to minimized the cumulative regret. We adapt a traditional Thompson Sampling algoirthm under the distributed sett…

Multi-Armed BanditsThompson Sampling

MOTS: Minimax Optimal Thompson Sampling

2020-03-03 · Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao 외

Thompson sampling is one of the most widely used algorithms for many online decision problems, due to its simplicity in implementation and superior empirical performance over other state-of-the-art methods. Despite its p…

Thompson Sampling