paper-with-me

홈 › Papers

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

2022-05-27 · Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz

We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with binary losses and adversarially-selected contexts. We adapt the information-theoretic perspective of \cite{RvR16} to the contextual setting by considering a lifted version of the information ratio defined in terms of the unknown model parameter instead of the optimal action or optimal policy as done in previous works on the same setting. This allows us to bound the regret in terms of the entropy of the prior distribution through a remarkably simple proof, and with no structural assumptions on the likelihood or the prior. The extension to priors with infinite entropy only requires a Lipschitz assumption on the log-likelihood. An interesting special case is that of logistic bandits with $d$-dimensional parameters, $K$ actions, and Lipschitz logits, for which we provide a $\widetilde{O}(\sqrt{dKT})$ regret upper-bound that does not depend on the smallest slope of the sigmoid link function.

📄 PDF Abstract BibTeX arXiv:2205.13924

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed BanditsThompson Sampling

Similar Papers 제목 키워드 기반

Learning-based safety lifting monitoring system for cranes on construction sites

2025-06-25 · Hao Chen, Yu Hin Ng, Ching-Wei Chang, Haobo Liang 외

Lifting on construction sites, as a frequent operation, works still with safety risks, especially for modular integrated construction (MiC) lifting due to its large weight and size, probably leading to accidents, causing…

Characterizing Tradeoffs in Language Model Decoding with Informational Interpretations

2023-11-16 · Chung-Ching Chang, William W. Cohen, Yun-Hsuan Sung

We propose a theoretical framework for formulating language model decoder algorithms with dynamic programming and information theory. With dynamic programming, we lift the design of decoder algorithms from the logit spac…

DecoderDiversityLanguage ModelingLanguage Modelling

Lifting Layers: Analysis and Applications

2018-03-23 · ECCV 2018 9 · Peter Ochs, Tim Meinhardt, Laura Leal-Taixe, Michael Moeller

The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suitable non-linearities. Interestingly, the…

Denoisingimage-classificationImage Classification

Lifting-based variational multiclass segmentation algorithm: design, convergence analysis, and implementation with applications in medical imaging

2022-02-09 · Nadja Gruber, Johannes Schwab, Sebastien Court, Elke Gizewski 외

We propose, analyze and realize a variational multiclass segmentation scheme that partitions a given image into multiple regions exhibiting specific properties. Our method determines multiple functions that encode the se…

Image SegmentationSegmentationSemantic Segmentation

Chained Generalisation Bounds

2022-03-02 · Eugenio Clerico, Amitis Shidani, George Deligiannidis, Arnaud Doucet

This work discusses how to derive upper bounds for the expected generalisation error of supervised learning algorithms by means of the chaining technique. By developing a general theoretical framework, we establish a dua…