mlsanityData to 7 Oct 2026

DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits

arXiv 2501.19401 ↗First posted 31 Jan 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce a practical, black-box framework termed Detection Augmented Learning (DAL) for the problem of piecewise stationary bandits without knowledge of the underlying non-stationarity. DAL accepts any stationary bandit algorithm with order-optimal regret as input and augments it with a change detector, enabling applicability to all common bandit variants. Extensive experimentation demonstrates that DAL consistently surpasses all state-of-the-art methods across diverse non-stationary scenarios, including synthetic benchmarks and real-world datasets, underscoring its versatility and scalability. We provide theoretical insights into DAL's strong empirical performance, complemented by thorough empirical validation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 66 references that are in the map. First posted on arXiv 31 Jan 2025.

Builds on

31 of 66 references.

References · 31

  1. 2017On Kernelized Multi-armed Banditscited by 348
  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. 2020Improved Optimistic Algorithms for Logistic Banditscited by 117
  5. 2021Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approachcited by 98
  6. 2017Real-Time Bidding by Reinforcement Learning in Display Advertisingcited by 90
  7. 2018Learning to Optimize under Non-Stationaritycited by 85
  8. 2019Weighted Linear Bandits for Non-Stationary Environmentscited by 84
  9. 2020Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluationcited by 77
  10. 2019A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-freecited by 71
  11. 2019Randomized Exploration in Generalized Linear Banditscited by 70
  12. 2021A Simple Approach for Non-stationary Linear Banditscited by 54
19 more
  1. 2018Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Banditcited by 49
  2. 2017A Change-Detection based Framework for Piecewise-stationary Multi-Armed Bandit Problemcited by 48
  3. 2022Jointly Efficient and Optimal Algorithms for Logistic Banditscited by 41
  4. 2021Weighted Gaussian Process Bandits for Non-stationary Environmentscited by 30
  5. 2020Self-Concordant Analysis of Generalized Linear Bandits with Forgettingcited by 29
  6. 2024A Unified Confidence Sequence for Generalized Linear Models, with Applications to Banditscited by 27
  7. 2020Algorithms for Non-Stationary Generalized Linear Banditscited by 23
  8. 2019Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory managementcited by 22
  9. 2017Attribution Modeling Increases Efficiency of Bidding in Display Advertisingcited by 19
  10. 2021No-Regret Algorithms for Time-Varying Bayesian Optimizationcited by 19
  11. 2018A Contextual-bandit-based Approach for Informed Decision-making in Clinical Trialscited by 18
  12. 2022An Optimization-based Algorithm for Non-stationary Kernel Bandits without Prior Knowledgecited by 17
  13. 2023Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiencycited by 16
  14. 2021Regret Bounds for Generalized Linear Bandits under Parameter Driftcited by 13
  15. 2021Finite-time Analysis of Globally Nonstationary Multi-Armed Banditscited by 7
  16. 2023The complexity of non-stationary reinforcement learningcited by 7
  17. 2019A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Banditscited by 5
  18. 2024Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?cited by 5
  19. 2025Sequential Change Detection for Learning in Piecewise Stationary Bandit Environmentscited by 5

Built on by

Not cited yet.