mlsanityData to 7 Oct 2026

Thompson Sampling with Approximate Inference

arXiv 1908.04970 ↗First posted 14 Aug 2019cs.LG stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

We study the effects of approximate inference on the performance of Thompson sampling in the k-armed bandit problems. Thompson sampling is a successful algorithm for online decision-making but requires posterior inference, which often must be approximated in practice. We show that even small constant inference error (in α-divergence) can lead to poor performance (linear regret) due to under-exploration (for α<1) or over-exploration (for α>0) by the approximation. While for α > 0 this is unavoidable, for α ≤ 0 the regret can be improved by adding a small amount of forced exploration even when the inference error is a large constant.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 4; 2023: 2; 2024: 2; 2025: 1.

15 papers.

Sort:

  1. 2021Bayesian decision-making under misspecified priors with applications to meta-learningcited by 43
  2. 2021From Predictions to Decisions: The Importance of Joint Predictive Distributionscited by 28
  3. 2023Low-rank extended Kalman filtering for online learning of neural networks from streaming datacited by 23
  4. 2022Langevin Monte Carlo for Contextual Banditscited by 22
  5. 2021Efficient Online Bayesian Inference for Neural Banditscited by 15
  6. 2024Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlocited by 10
  7. 2022Fast online inference for nonlinear contextual bandit based on Generative Adversarial Networkcited by 7
  8. 2021Bayesian brains and the R'enyi divergencecited by 6
  9. 2021Variational Bayesian Optimistic Samplingcited by 6
  10. 2025Martingale Posterior Neural Networks for Fast Sequential Decision Makingcited by 4
  11. 2022Remote Contextual Banditscited by 3
  12. 2023Multiplier Bootstrap-based Explorationcited by 3
3 more
  1. 2022Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Frameworkcited by 2
  2. 2021Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Banditcited by 0
  3. 2024Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Banditscited by 0