paper-with-me

Papers

Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox

2024-10-07 · Raymond Zhang, Richard Combes

We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched sampling paradox": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatched-Paradox

📄 PDF Abstract BibTeX arXiv:2410.05441

Code (1)

raymzhang/cts-mismatched-paradox 공식 구현

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

Combinatorial Neural Bandits

2023-05-31 · TaeHyun Hwang, Kyuwook Chai, Min-hwan Oh

We consider a contextual combinatorial bandit problem where in each round a learning agent selects a subset of arms and receives feedback on the selected arms according to their scores. The score of an arm is an unknown …

Thompson Sampling

Worst-Case Regret Bounds for Combinatorial Thompson Sampling in Sleeping Semi-Bandits

2026-05-10 · Zhiming Huang, Bingshan Hu, Jianping Pan arxiv

We revisit combinatorial Thompson sampling (CTS) for semi-bandits with sleeping arms, where arm availability varies over time and actions must satisfy combinatorial constraints, as in wireless mesh routing with fluctuati…

Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths

2026-07-16 · Guni Sharon, Wei Zhang arxiv

We introduce Stochastic Reset Pathfinding (SRP), an episodic learning problem on a known directed graph with unknown stationary edge success probabilities. In each episode, the agent commits to a source-to-goal path, and…

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

Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits

2020-06-11 · NeurIPS 2020 12 · Pierre Perrault, Etienne Boursier, Vianney Perchet, Michal Valko

We investigate stochastic combinatorial multi-armed bandit with semi-bandit feedback (CMAB). In CMAB, the question of the existence of an efficient policy with an optimal asymptotic regret (up to a factor poly-logarithmi…

Thompson Sampling