mlsanityData to 7 Oct 2026

Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications

arXiv 2302.03683 ↗First posted 7 Feb 2023cs.LG stat.MLcited by 11

Not on the map. Why?

Abstract (arXiv)

Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey and extend recent results on the linear formulation of partial monitoring that naturally generalizes the standard linear bandit setting. The main result is that a single algorithm, information-directed sampling (IDS), is (nearly) worst-case rate optimal in all finite-action games. We present a simple and unified analysis of stochastic partial monitoring, and further extend the model to the contextual and kernelized setting.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 32 of its 71 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

32 of 71 references.

References · 32

  1. 2021Convex optimizationcited by 2,479
  2. 2021The Statistical Complexity of Interactive Decision Makingcited by 208
  3. 2018Gaussian Processes and Kernel Methods: A Review on Connections and Equivalencescited by 188
  4. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  5. 2014Learning to Optimize via Information-Directed Samplingcited by 168
  6. 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 156
  7. 2018Preference-based Online Learning with Dueling Bandits: A Surveycited by 100
  8. 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
  9. 2017Mostly Exploration-Free Algorithms for Contextual Banditscited by 85
  10. 2018Information Directed Sampling and Bandits with Heteroscedastic Noisecited by 75
  11. 2021Reinforcement Learning, Bit by Bitcited by 59
  12. 2018Information-Directed Exploration for Deep Reinforcement Learningcited by 52
20 more
  1. 2016The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Banditscited by 48
  2. 2019Adaptive Exploration in Linear Contextual Banditcited by 43
  3. 2019An Information-Theoretic Approach to Minimax Regret in Partial Monitoringcited by 41
  4. 2017Minimal Exploration in Structured Stochastic Banditscited by 40
  5. 2020Information Directed Sampling for Linear Partial Monitoringcited by 39
  6. 2020Mirror Descent and the Information Ratiocited by 39
  7. 2020Asymptotically Optimal Information-Directed Samplingcited by 33
  8. 2020An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Banditscited by 26
  9. 2017Information Directed Sampling for Stochastic Bandits with Graph Feedbackcited by 24
  10. 2022Regret Bounds for Information-Directed Reinforcement Learningcited by 24
  11. 2019Exploration by Optimisation in Partial Monitoringcited by 20
  12. 2018Cleaning up the neighborhood: A full classification for adversarial partial monitoringcited by 16
  13. 2022Contextual Information-Directed Samplingcited by 16
  14. 2020Hard Shape-Constrained Kernel Machinescited by 13
  15. 2021Bias-Robust Bayesian Optimization via Dueling Banditscited by 11
  16. 2015Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoringcited by 10
  17. 2020Analysis and Design of Thompson Sampling for Stochastic Partial Monitoringcited by 9
  18. 2021A Short Note on the Relationship of Information Gain and Eluder Dimensioncited by 7
  19. 2015Utility-based Dueling Bandits as a Partial Monitoring Gamecited by 4
  20. 2016Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Gamescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 3; 2026: 1.

11 papers.

  1. 2024Beyond Optimism: Exploration With Partially Observable Rewardscited by 6
  2. 2024Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraintscited by 2
  3. 2024Randomized Confidence Bounds for Stochastic Partial Monitoringcited by 2
  4. 2024Regret Minimization via Saddle Point Optimizationcited by 2
  5. 2025Infinite-Dimensional Operator/Block Kaczmarz Algorithms: Regret Bounds and λ-Effectivenesscited by 2
  6. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  7. 2024Adversarial Multi-dueling Banditscited by 1
  8. 2024Indirect Query Bayesian Optimization with Integrated Feedbackcited by 1
  9. 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoringcited by 1
  10. 2025Bayesian Optimization for General Reaction Conditionscited by 0
  11. 2026The Delegation Blind Spot: Auditing Product Decisions from Agent Choicescited by 0