paper-with-me

홈 › Papers

Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits

2023-02-03 · Jongyeong Lee, Junya Honda, Chao-Kai Chiang, Masashi Sugiyama

In the stochastic multi-armed bandit problem, a randomized probability matching policy called Thompson sampling (TS) has shown excellent performance in various reward models. In addition to the empirical performance, TS has been shown to achieve asymptotic problem-dependent lower bounds in several models. However, its optimality has been mainly addressed under light-tailed or one-parameter models that belong to exponential families. In this paper, we consider the optimality of TS for the Pareto model that has a heavy tail and is parameterized by two unknown parameters. Specifically, we discuss the optimality of TS with probability matching priors that include the Jeffreys prior and the reference priors. We first prove that TS with certain probability matching priors can achieve the optimal regret bound. Then, we show the suboptimality of TS with other priors, including the Jeffreys and the reference priors. Nevertheless, we find that TS with the Jeffreys and reference priors can achieve the asymptotic lower bound if one uses a truncation procedure. These results suggest carefully choosing noninformative priors to avoid suboptimality and show the effectiveness of truncation procedures in TS-based policies.

📄 PDF Abstract BibTeX arXiv:2302.01544

Code (0)

등록된 구현이 없습니다.

Tasks

Thompson Sampling

Methods 이 논문이 사용한 방법론

TS Spatio-temporal features extraction that measure the stabilty. The proposed method is based on a compression algorithm named Run Length Encoding. The workflow of the method is…

Similar Papers 제목 키워드 기반

The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models

2023-02-28 · Jongyeong Lee, Chao-Kai Chiang, Masashi Sugiyama

Thompson sampling (TS) has been known for its outstanding empirical performance supported by theoretical guarantees across various reward models in the classical stochastic multi-armed bandit problems. Nonetheless, its o…

Multi-Armed BanditsThompson Sampling

Nonparametric General Reinforcement Learning

2016-11-28 · Jan Leike

Reinforcement learning (RL) problems are often phrased in terms of Markov decision processes (MDPs). In this thesis we go beyond MDPs and consider RL in environments that are non-Markovian, non-ergodic and only partially…

General Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

On the Suboptimality of Thompson Sampling in High Dimensions

2021-02-10 · NeurIPS 2021 12 · Raymond Zhang, Richard Combes

In this paper we consider Thompson Sampling (TS) for combinatorial semi-bandits. We demonstrate that, perhaps surprisingly, TS is sub-optimal for this problem in the sense that its regret scales exponentially in the ambi…

Thompson SamplingVocal Bursts Intensity Prediction

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

A study of Thompson Sampling with Parameter h

2017-10-05 · Qiang Ha

Thompson Sampling algorithm is a well known Bayesian algorithm for solving stochastic multi-armed bandit. At each time step the algorithm chooses each arm with probability proportional to it being the current best arm. W…

Thompson Sampling