mlsanityData to 7 Oct 2026

Information Directed Sampling for Linear Partial Monitoring

arXiv 2002.11182 ↗First posted 25 Feb 2020stat.ML cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Partial monitoring is a rich framework for sequential decision making under uncertainty that generalizes many well known bandit models, including linear, combinatorial and dueling bandits. We introduce information directed sampling (IDS) for stochastic partial monitoring with a linear reward and observation structure. IDS achieves adaptive worst-case regret rates that depend on precise observability conditions of the game. Moreover, we prove lower bounds that classify the minimax regret of all finite games into four possible regimes. IDS achieves the optimal rate in all cases up to logarithmic factors, without tuning any hyper-parameters. We further extend our results to the contextual and the kernelized setting, which significantly increases the range of possible applications.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 2; 2024: 12; 2025: 5; 2026: 3.

39 papers.

Sort:

By area:

  1. 2021Reinforcement Learning, Bit by Bitcited by 59
  2. 2022On the Complexity of Adversarial Decision Makingcited by 32
  3. 2021Information Directed Reward Learning for Reinforcement Learningcited by 24
  4. 2022Regret Bounds for Information-Directed Reinforcement Learningcited by 24
  5. 2021Information Directed Sampling for Sparse Linear Banditscited by 20
  6. 2021Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedbackcited by 19
  7. 2022Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Banditscited by 19
  8. 2022Contextual Information-Directed Samplingcited by 16
  9. 2021Bandit Phase Retrievalcited by 12
  10. 2021Bias-Robust Bayesian Optimization via Dueling Banditscited by 11
  11. 2022Near-Optimal Multi-Agent Learning for Safe Coverage Controlcited by 11
  12. 2023Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applicationscited by 11
27 more
  1. 2024Optimistic Information Directed Samplingcited by 7
  2. 2024Bandits with Preference Feedback: A Stackelberg Game Perspectivecited by 7
  3. 2024Beyond Optimism: Exploration With Partially Observable Rewardscited by 6
  4. 2021A Bit Better? Quantifying Information for Bandit Learningcited by 5
  5. 2022Gaussian Imagination in Bandit Learningcited by 5
  6. 2024Thompson Sampling in Partially Observable Contextual Banditscited by 5
  7. 2023Online Decision Mediationcited by 4
  8. 2024Robustifying and Boosting Training-Free Neural Architecture Searchcited by 4
  9. 2022The price of unfairness in linear bandits with biased feedbackcited by 3
  10. 2024Provably Efficient Interactive-Grounded Learning with Personalized Rewardcited by 3
  11. 2021Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classificationcited by 2
  12. 2024Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraintscited by 2
  13. 2024Randomized Confidence Bounds for Stochastic Partial Monitoringcited by 2
  14. 2024Regret Minimization via Saddle Point Optimizationcited by 2
  15. 2024Indexed Minimum Empirical Divergence-Based Algorithms for Linear Banditscited by 2
  16. 2022Non-Stationary Dynamic Pricing Via Actor-Critic Information-Directed Pricingcited by 1
  17. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  18. 2024Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Boundscited by 1
  19. 2025Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoringcited by 1
  20. 2025Sparse Optimistic Information Directed Samplingcited by 1
  21. 2022Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Searchcited by 0
  22. 2025Empirical Bound Information-Directed Sampling for Norm-Agnostic Banditscited by 0
  23. 2025Best-of-Both Worlds for linear contextual bandits with paid observationscited by 0
  24. 2025Information-directed sampling for bandits: a primercited by 0
  25. 2026Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedbackcited by 0
  26. 2026Future Information-Directed Sampling for Bayesian Nonstationary Banditscited by 0
  27. 2026Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairnesscited by 0