mlsanityData to 14 Oct 2026

Randomized Exploration in Generalized Linear Bandits

arXiv 1906.08947 ↗First posted 21 Jun 2019cs.LG stat.MLcited by 70

Not on the map. Why?

Abstract (arXiv)

We study two randomized algorithms for generalized linear bandits. The first, GLM-TSL, samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution. The second, GLM-FPL, fits a GLM to a randomly perturbed history of past rewards. We analyze both algorithms and derive tildeO(d √n log K) upper bounds on their n-round regret, where d is the number of features and K is the number of arms. The former improves on prior work while the latter is the first for Gaussian noise perturbations in non-linear models. We empirically evaluate both GLM-TSL and GLM-FPL in logistic bandits, and apply GLM-FPL to neural network bandits. Our work showcases the role of randomization, beyond posterior sampling, in exploration.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 16; 2023: 10; 2024: 16; 2025: 14; 2026: 7.

70 papers.

Sort:

By area:

  1. 2021Randomized Exploration for Reinforcement Learning with General Value Function Approximationcited by 49
  2. 2022Jointly Efficient and Optimal Algorithms for Logistic Banditscited by 41
  3. 2022A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learningcited by 31
  4. 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Banditscited by 29
  5. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  6. 2023Random Boxes Are Open-world Object Detectorscited by 24
  7. 2023Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversioncited by 24
  8. 2021Fixed-Budget Best-Arm Identification in Structured Banditscited by 22
  9. 2022Langevin Monte Carlo for Contextual Banditscited by 22
  10. 2021Multinomial Logit Contextual Bandits: Provable Optimality and Practicalitycited by 21
  11. 2024Nearly Minimax Optimal Regret for Multinomial Logistic Banditcited by 20
  12. 2021Understanding the Eluder Dimensioncited by 19
38 more
  1. 2022Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Banditscited by 19
  2. 2022Learning Neural Contextual Bandits Through Perturbed Rewardscited by 17
  3. 2022Active Learning with Safety Constraintscited by 16
  4. 2022Model-Based Reinforcement Learning with Multinomial Logistic Function Approximationcited by 13
  5. 2023Exploration via linearly perturbed loss minimisationcited by 13
  6. 2021Diffusion Approximations for Thompson Sampling in the Small Gap Regimecited by 12
  7. 2022Towards Scalable and Robust Structured Bandits: A Meta-Learning Frameworkcited by 11
  8. 2025Active Learning for Direct Preference Optimizationcited by 10
  9. 2022Residual Bootstrap Exploration for Stochastic Linear Banditcited by 8
  10. 2025When and why randomised exploration works (in linear bandits)cited by 8
  11. 2025Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuningcited by 8
  12. 2024Causal Bandits with General Causal Models and Interventionscited by 7
  13. 2023VITS : Variational Inference Thompson Sampling for contextual banditscited by 6
  14. 2024Active Preference Learning for Ordering Items In- and Out-of-samplecited by 6
  15. 2024Random Latent Exploration for Deep Reinforcement Learningcited by 6
  16. 2024Improved Regret of Linear Ensemble Samplingcited by 6
  17. 2025Neural Logistic Banditscited by 6
  18. 2025Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functionscited by 6
  19. 2024Diffusion Models Meet Contextual Banditscited by 5
  20. 2024Conversational Dueling Bandits in Generalized Linear Modelscited by 5
  21. 2022Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Armscited by 4
  22. 2024Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Banditscited by 4
  23. 2024AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analyticscited by 4
  24. 2025Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdowncited by 4
  25. 2025No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processescited by 4
  26. 2022IMO3: Interactive Multi-Objective Off-Policy Optimizationcited by 3
  27. 2023Multiplier Bootstrap-based Explorationcited by 3
  28. 2023Does Sparsity Help in Learning Misspecified Linear Bandits?cited by 3
  29. 2024Variance-Aware Linear UCB with Deep Representation for Neural Contextual Banditscited by 3
  30. 2022Reward-Biased Maximum Likelihood Estimation for Neural Contextual Banditscited by 2
  31. 2023Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health studycited by 2
  32. 2023Fair Active Learning in Low-Data Regimescited by 2
  33. 2024Online Posterior Sampling with a Diffusion Priorcited by 2
  34. 2025Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Explorationcited by 2
  35. 2025Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Banditscited by 2
  36. 2026DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Modelscited by 2
  37. 2021An Efficient Algorithm for Deep Stochastic Contextual Banditscited by 1
  38. 2022Truncated LinUCB for Stochastic Linear Banditscited by 1

50 most cited of 70 All 70 (JSON)