mlsanityData to 7 Oct 2026

Contextual Multinomial Logit Bandits with General Value Functions

arXiv 2402.08126 ↗First posted 12 Feb 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Contextual multinomial logit (MNL) bandits capture many real-world assortment recommendation problems such as online retailing/advertising. However, prior work has only considered (generalized) linear value functions, which greatly limits its applicability. Motivated by this fact, in this work, we consider contextual MNL bandits with a general value function class that contains the ground truth, borrowing ideas from a recent trend of studies on contextual bandits. Specifically, we consider both the stochastic and the adversarial settings, and propose a suite of algorithms, each with different computation-regret trade-off. When applied to the linear case, our results not only are the first ones with no dependence on a certain problem-dependent constant that can be exponentially large, but also enjoy other advantages such as computational efficiency, dimension-free regret bounds, or the ability to handle completely adversarial contexts and rewards.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

23 of 32 references.

References · 23

  1. 2021The Statistical Complexity of Interactive Decision Makingcited by 208
  2. 2014Taming the Monster: A Fast and Simple Algorithm for Contextual Banditscited by 200
  3. 2020Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oraclescited by 195
  4. 2020Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizabilitycited by 114
  5. 2021Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learningcited by 65
  6. 2021Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discriminationcited by 53
  7. 2017MNL-Bandit: A Dynamic Learning Approach to Assortment Selectioncited by 50
  8. 2015Fast rates in statistical and online learningcited by 47
  9. 2018Logistic Regression: The Importance of Being Impropercited by 40
  10. 2017Thompson Sampling for the MNL-Banditcited by 35
  11. 2020Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Banditscited by 35
  12. 2022On the Complexity of Adversarial Decision Makingcited by 32
11 more
  1. 2018Dynamic Assortment Optimization with Changing Contextual Informationcited by 28
  2. 2016Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayescited by 27
  3. 2021Multinomial Logit Contextual Bandits: Provable Optimality and Practicalitycited by 21
  4. 2021Dynamic pricing and assortment under a contextual MNL demandcited by 20
  5. 2022Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spacescited by 17
  6. 2018Multinomial Logit Bandit with Linear Utility Functionscited by 15
  7. 2020A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Banditcited by 15
  8. 2021Adversarial Combinatorial Bandits with General Non-linear Reward Functionscited by 14
  9. 2020Multinomial Logit Bandit with Low Switching Costcited by 10
  10. 2023Practical Contextual Bandits with Feedback Graphscited by 10
  11. 2023Online Learning in Contextual Second-Price Pay-Per-Click Auctionscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2024Nearly Minimax Optimal Regret for Multinomial Logistic Banditcited by 20
  2. 2026Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actionscited by 2
  3. 2026Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilitiescited by 0
  4. 2026Diversified Multinomial Logit Contextual Banditscited by 0