mlsanityData to 7 Oct 2026

Cascading Bandits: Learning to Rank in the Cascade Model

arXiv 1502.02763 ↗First posted 10 Feb 2015cs.LG stat.MLcited by 75

Not on the map. Why?

Abstract (arXiv)

A search engine usually outputs a list of K web pages. The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user behavior is known as the cascade model. In this paper, we propose cascading bandits, a learning variant of the cascade model where the objective is to identify K most attractive items. We formulate our problem as a stochastic combinatorial partial monitoring problem. We propose two algorithms for solving it, CascadeUCB1 and CascadeKL-UCB. We also prove gap-dependent upper bounds on the regret of these algorithms and derive a lower bound on the regret in cascading bandits. The lower bound matches the upper bound of CascadeKL-UCB up to a logarithmic factor. We experiment with our algorithms on several problems. The algorithms perform surprisingly well even when our modeling assumptions are violated.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 14; 2023: 13; 2024: 9; 2025: 9; 2026: 9.

75 papers.

Sort:

By area:

  1. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  2. 2024Cost-Effective Online Multi-LLM Selection with Versatile Reward Modelscited by 36
  3. 2021Hierarchical Bayesian Banditscited by 33
  4. 2021Multinomial Logit Contextual Bandits: Provable Optimality and Practicalitycited by 21
  5. 2021Measuring Recommender System Effects with Simulated Userscited by 20
  6. 2021Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalizationcited by 18
  7. 2022Deep Hierarchy in Banditscited by 18
  8. 2024Optimal Design for Human Preference Elicitationcited by 17
  9. 2023Combinatorial Neural Banditscited by 16
  10. 2022Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Armscited by 15
  11. 2026A Survey on LLM-based Conversational User Simulationcited by 14
  12. 2022Towards Scalable and Robust Structured Bandits: A Meta-Learning Frameworkcited by 10
38 more
  1. 2022Minimax Regret for Cascading Banditscited by 10
  2. 2025Active Learning for Direct Preference Optimizationcited by 9
  3. 2022Fast online inference for nonlinear contextual bandit based on Generative Adversarial Networkcited by 7
  4. 2024Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyondcited by 7
  5. 2021Be Greedy in Multi-Armed Banditscited by 6
  6. 2021Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rankcited by 6
  7. 2021PairRank: Online Pairwise Learning to Rank by Divide-and-Conquercited by 6
  8. 2022Federated Multi-Armed Bandits Under Byzantine Attackscited by 6
  9. 2022Online Learning and Bandits with Queried Hintscited by 6
  10. 2023Adversarial Attacks on Online Learning to Rank with Click Feedbackcited by 6
  11. 2023Competing for Shareable Arms in Multi-Player Multi-Armed Banditscited by 6
  12. 2023Adversarial Attacks on Online Learning to Rank with Stochastic Click Modelscited by 6
  13. 2024Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Userscited by 6
  14. 2024Probably Approximately Precision and Recall Learningcited by 5
  15. 2025Offline Learning for Combinatorial Multi-armed Banditscited by 5
  16. 2021Safe Data Collection for Offline and Online Policy Learningcited by 4
  17. 2024Cascading Reinforcement Learningcited by 4
  18. 2025Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequalitycited by 4
  19. 2021Conservative Contextual Combinatorial Cascading Banditcited by 3
  20. 2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
  21. 2022Product Ranking for Revenue Maximization with Multiple Purchasescited by 3
  22. 2023Multiplier Bootstrap-based Explorationcited by 3
  23. 2023Sum-max Submodular Banditscited by 3
  24. 2021Sequential Choice Bandits with Feedback for Personalizing users' experiencecited by 2
  25. 2021Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processescited by 2
  26. 2021On Submodular Contextual Banditscited by 2
  27. 2022Pessimistic Off-Policy Optimization for Learning to Rankcited by 2
  28. 2022Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Modelcited by 2
  29. 2022Contextual bandits with concave rewards, and an application to fair rankingcited by 2
  30. 2023Adversarial Attacks on Combinatorial Multi-Armed Banditscited by 2
  31. 2025Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problemscited by 2
  32. 2026Efficient Adversarial Attacks on High-dimensional Offline Banditscited by 2
  33. 2026Multi-Armed Bandits With Best-Action Queriescited by 2
  34. 2021CORe: Capitalizing On Rewards in Bandit Explorationcited by 1
  35. 2021Cascading Bandit under Differential Privacycited by 1
  36. 2021Online Learning of Independent Cascade Models with Node-level Feedbackcited by 1
  37. 2021Online Learning of Optimally Diverse Rankingscited by 1
  38. 2021Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rankcited by 1

50 most cited of 75 All 75 (JSON)