mlsanityData to 14 Oct 2026

Neural Logistic Bandits

arXiv 2505.02069 ↗First posted 4 May 2025cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a neural network. Existing approaches either exhibit unfavorable dependencies on kappa, where 1/kappa represents the minimum variance of reward distributions, or suffer from direct dependence on the feature dimension d, which can be huge in neural network-based settings. In this work, we introduce a novel Bernstein-type inequality for self-normalized vector-valued martingales that is designed to bypass a direct dependence on the ambient dimension. This lets us deduce a regret upper bound that grows with the effective dimension widetilded, not the feature dimension, while keeping a minimal dependence on kappa. Based on the concentration inequality, we propose two algorithms, NeuralLog-UCB-1 and NeuralLog-UCB-2, that guarantee regret upper bounds of order widetildeO(widetilded√kappa T) and widetildeO(widetilded√T/kappa), respectively, improving on the existing results. Lastly, we report numerical results on both synthetic and real datasets to validate our theoretical findings.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 4 May 2025.

Builds on

27 of 38 references.

References · 27

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  2. 2020Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processescited by 200
  3. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  4. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 169
  5. 2020Neural Thompson Samplingcited by 128
  6. 2020Improved Optimistic Algorithms for Logistic Banditscited by 118
  7. 2020Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluationcited by 77
  8. 2020Neural Contextual Bandits with Deep Representation and Shallow Explorationcited by 71
  9. 2019Randomized Exploration in Generalized Linear Banditscited by 70
  10. 2020Instance-Wise Minimax-Optimal Algorithms for Logistic Banditscited by 57
  11. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 44
  12. 2021Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPscited by 44
15 more
  1. 2020Nearly Minimax Optimal Reinforcement Learning for Discounted MDPscited by 42
  2. 2022Jointly Efficient and Optimal Algorithms for Logistic Banditscited by 41
  3. 2021Neural Contextual Bandits without Regretcited by 40
  4. 2019On the Performance of Thompson Sampling on Logistic Banditscited by 32
  5. 2020Improved Confidence Bounds for the Linear Logistic Model and Applications to Linear Banditscited by 31
  6. 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Banditscited by 29
  7. 2023Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversioncited by 24
  8. 2024Generalized Linear Bandits with Limited Adaptivitycited by 22
  9. 2024Nearly Minimax Optimal Regret for Multinomial Logistic Banditcited by 20
  10. 2019Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matchingcited by 17
  11. 2022Learning Neural Contextual Bandits Through Perturbed Rewardscited by 17
  12. 2025Improved Online Confidence Bounds for Multinomial Logistic Banditscited by 15
  13. 2022Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Banditscited by 14
  14. 2022Norm-Agnostic Linear Banditscited by 12
  15. 2024Neural Dueling Bandits: Preference-Based Optimization with Human Feedbackcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Boundscited by 4
  2. 2026Queue Length Regret Bounds for Contextual Queueing Banditscited by 4
  3. 2026Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regretcited by 2
  4. 2026Logistic Bandits with tildeO(√dT) Regret without Context Diversity Assumptionscited by 1
  5. 2026CASCADE: Case-Based Continual Adaptation for Large Language Models During Deploymentcited by 1
  6. 2026Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairnesscited by 0