mlsanityData to 14 Oct 2026

Bayesian Online Model Selection

arXiv 2602.17958 ↗First posted 20 Feb 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Online model selection in Bayesian bandits raises a fundamental exploration challenge: When an environment instance is sampled from a prior distribution, how can we design an adaptive strategy that explores multiple bandit learners and competes with the best one in hindsight? We address this problem by introducing a new Bayesian algorithm for online model selection in stochastic bandits. We prove an oracle-style guarantee of Oleft( d^* M √T + √(MT) right) on the Bayesian regret, where M is the number of base learners, d^* is the regret coefficient of the optimal base learner, and T is the time horizon. We also validate our method empirically across a range of stochastic bandit settings, demonstrating performance that is competitive with the best base learner. Additionally, we study the effect of sharing data among base learners and its role in mitigating prior mis-specification.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 27 references that are in the map. First posted on arXiv 20 Feb 2026.

Builds on

15 of 27 references.

References · 15

  1. 2017A Tutorial on Thompson Samplingcited by 433
  2. 2016Corralling a Band of Bandit Algorithmscited by 100
  3. 2020Model Selection in Contextual Stochastic Bandit Problemscited by 71
  4. 2021Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learningcited by 66
  5. 2021Meta-Thompson Samplingcited by 63
  6. 2020Regret Bound Balancing and Elimination for Model Selection in Bandits and RLcited by 47
  7. 2023Foundations of Reinforcement Learning and Interactive Decision Makingcited by 33
  8. 2021The Pareto Frontier of model selection for general Contextual Banditscited by 24
  9. 2021Thompson Sampling with a Mixture Priorcited by 16
  10. 2022Model-based Lifelong Reinforcement Learning with Bayesian Explorationcited by 12
  11. 2023Data-Driven Online Model Selection With Regret Guaranteescited by 11
  12. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
3 more
  1. 2024Experiment Planning with Function Approximationcited by 5
  2. 2024Diffusion Models Meet Contextual Banditscited by 5
  3. 2025On the Hardness of Bandit Learningcited by 2

Built on by

Not cited yet.