mlsanityData to 14 Oct 2026

Delayed Feedback in Generalised Linear Bandits Revisited

arXiv 2207.10786 ↗First posted 21 Jul 2022cs.LG stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

The stochastic generalised linear bandit is a well-understood model for sequential decision-making problems, with many algorithms achieving near-optimal regret guarantees under immediate feedback. However, the stringent requirement for immediate rewards is unmet in many real-world applications where the reward is almost always delayed. We study the phenomenon of delayed rewards in generalised linear bandits in a theoretical manner. We show that a natural adaptation of an optimistic algorithm to the delayed feedback achieves a regret bound where the penalty for the delays is independent of the horizon. This result significantly improves upon existing work, where the best known regret bound has the delay penalty increasing with the horizon. We verify our theoretical results through experiments on simulated data.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 8 of its 29 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

8 of 29 references.

References · 8

  1. 2013Learning to Optimize Via Posterior Samplingcited by 256
  2. 2013Online Learning under Delayed Feedbackcited by 141
  3. 2020Improved Optimistic Algorithms for Logistic Banditscited by 118
  4. 2017Scalable Generalized Linear Bandits: Online Computation and Hashingcited by 64
  5. 2018Linear Bandits with Stochastic Delayed Feedbackcited by 55
  6. 2017Stochastic Bandit Models for Delayed Conversionscited by 54
  7. 2017Provably Optimal Algorithms for Generalized Linear Contextual Banditscited by 38
  8. 2020Delay-Adaptive Learning in Generalized Linear Contextual Banditscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 6; 2026: 5.

23 papers.

Sort:

By area:

  1. 2024SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengthscited by 75
  2. 2023A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPscited by 15
  3. 2023Delayed Feedback in Kernel Banditscited by 10
  4. 2023A Reduction-based Framework for Sequential Decision Making with Delayed Feedbackcited by 7
  5. 2023Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedbackcited by 6
  6. 2024Delay as Payoff in MABcited by 6
  7. 2025Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedbackcited by 5
  8. 2023Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observationscited by 4
  9. 2023Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximationcited by 3
  10. 2024Biased Dueling Bandits with Stochastic Delayed Feedbackcited by 3
  11. 2025Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedbackcited by 2
  12. 2023Stochastic Contextual Bandits with Long Horizon Rewardscited by 1
11 more
  1. 2024Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensitycited by 1
  2. 2025Lipschitz Bandits with Stochastic Delayed Feedbackcited by 1
  3. 2026Batched Stochastic Linear Bandits with 1-Bit Communication Constraintscited by 1
  4. 2024Risk-averse learning with delayed feedbackcited by 0
  5. 2025Neural Contextual Bandits Under Delayed Feedback Constraintscited by 0
  6. 2025Linear Bandits with Non-i.i.d. Noisecited by 0
  7. 2025Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encodingcited by 0
  8. 2026Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learningcited by 0
  9. 2026Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptionscited by 0
  10. 2026Near-Optimal Stochastic Linear Bandits with Delaycited by 0
  11. 2026Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochscited by 0