COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Information Theory Seminar > Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Analysis
Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic AnalysisAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Dr Varun Jog. Decision-making in the face of uncertainty is a practical challenge found across various areas such as control and robotics, clinical trials, communication, and ecology. An extensively studied decision-making framework is that of stochastic contextual bandits (CBs) which uses side information, termed context, for sequential decision making. Prior research on CBs has mostly focussed on models where the contexts are well-defined. This, however, is not true in real-world applications where the contexts are either noisy or are indicative of predictive measurements. In this talk, we focus on noisy CBs where the learner observes only a noisy, corrupted, version of the true context through an unknown noise channel. We introduce a Thompson Sampling algorithm for Gaussian bandits with Gaussian context noise that can ‘approximate’ the action policy of an oracle which has access to the predictive distribution of the true context from the observed noisy context. Using information-theoretic tools, we study the Bayesian regret of the proposed algorithm. This talk is part of the Information Theory Seminar series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsType the title of a new list here Data mining Cafe RSAOther talksStrong deformation of 3D cellular aggregates: from cellular deformation to elastocapillarity Wheeler Lecture 2023: Beyond functional programming: a taste of Verse Gravitational Observatories First in human evaluation of CDK9 inhibition with KB-0742 in solid tumors Using Fine-resolution Contact Tracing Data to Understand Population-scale Social Mixing Patterns and Infection Dynamics Computational thinking in primary schooling: Thinking beyond computer science |