mlsanityData to 7 Oct 2026

Bayesian Optimization under Stochastic Delayed Feedback

arXiv 2206.09341 ↗First posted 19 Jun 2022cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization of complex and expensive-to-compute black-box functions. The existing BO methods assume that the function evaluation (feedback) is available to the learner immediately or after a fixed delay. Such assumptions may not be practical in many real-life problems like online recommendations, clinical trials, and hyperparameter tuning where feedback is available after a random delay. To benefit from the experimental parallelization in these problems, the learner needs to start new function evaluations without waiting for delayed feedback. In this paper, we consider the BO under stochastic delayed feedback problem. We propose algorithms with sub-linear regret guarantees that efficiently address the dilemma of selecting new function queries while waiting for randomly delayed feedback. Building on our results, we also make novel contributions to batch BO and contextual Gaussian process bandits. Experiments on synthetic and real-life datasets verify the performance of our algorithms.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 44 of its 85 references that are in the map. First posted on arXiv 19 Jun 2022.

Builds on

44 of 85 references.

References · 44

  1. 2018A Tutorial on Bayesian Optimizationcited by 734
  2. 2019Introduction to Multi-Armed Banditscited by 475
  3. 2017On Kernelized Multi-armed Banditscited by 348
  4. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  5. 2013Online Learning under Delayed Feedbackcited by 137
  6. 2015Batch Bayesian Optimization via Local Penalizationcited by 103
  7. 2020Federated Bayesian Optimization via Thompson Samplingcited by 77
  8. 2018What Doubling Tricks Can and Can't Do for Multi-Armed Banditscited by 69
  9. 2021Gaussian Process Bandit Optimization with Few Batchescited by 57
  10. 2018Linear Bandits with Stochastic Delayed Feedbackcited by 55
  11. 2017Stochastic Bandit Models for Delayed Conversionscited by 53
  12. 2013Parallel Gaussian Process Optimization with Upper Confidence Bound and Pure Explorationcited by 50
32 more
  1. 2021Differentially Private Federated Bayesian Optimization with Distributed Explorationcited by 32
  2. 2018Best arm identification in multi-armed bandits with delayed feedbackcited by 29
  3. 2021NASI: Label- and Data-agnostic Neural Architecture Search at Initializationcited by 28
  4. 2017Decentralized High-Dimensional Bayesian Optimization with Factor Graphscited by 23
  5. 2020Top-k Ranking Bayesian Optimizationcited by 21
  6. 2017Attribution Modeling Increases Efficiency of Bidding in Display Advertisingcited by 19
  7. 2021Value-at-Risk Optimization with Gaussian Processescited by 19
  8. 2018Bandit Online Learning with Unknown Delayscited by 18
  9. 2019Implicit Posterior Variational Inference for Deep Gaussian Processescited by 17
  10. 2020Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimizationcited by 16
  11. 2015Gaussian Process Planning with Lipschitz Continuous Reward Functions: Towards Unifying Bayesian Optimization, Active Learning, and Beyondcited by 15
  12. 2019Bayesian Optimization with Binary Auxiliary Informationcited by 15
  13. 2020Private Outsourced Bayesian Optimizationcited by 15
  14. 2020An Information-Theoretic Framework for Unifying Active Learning Problemscited by 14
  15. 2019Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedbackcited by 13
  16. 2019On Batch Bayesian Optimizationcited by 12
  17. 2020R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Gamescited by 11
  18. 2020Nonmyopic Gaussian Process Optimization with Macro-Actionscited by 8
  19. 2021Trusted-Maximizers Entropy Search for Efficient Bayesian Optimizationcited by 8
  20. 2022On Provably Robust Meta-Bayesian Optimizationcited by 8
  21. 2021Neural Ensemble Search via Bayesian Samplingcited by 7
  22. 2014GP-Localize: Persistent Mobile Robot Localization using Online Sparse Gaussian Process Observation Modelcited by 6
  23. 2013Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximationscited by 5
  24. 2016A Generalized Stochastic Variational Bayesian Hyperparameter Learning Framework for Sparse Spectrum Gaussian Process Regressioncited by 5
  25. 2017Asynchronous Parallel Empirical Variance Guided Algorithms for the Thresholding Bandit Problemcited by 5
  26. 2020Stochastic Network Utility Maximization with Unknown Utilities: Multi-Armed Bandits Approachcited by 5
  27. 2013Gaussian Process-Based Decentralized Data Fusion and Active Sensing for Mobility-on-Demand Systemcited by 4
  28. 2017Gaussian Process Decentralized Data Fusion Meets Transfer Learning in Large-Scale Distributed Cooperative Perceptioncited by 4
  29. 2021Censored Semi-Bandits for Resource Allocationcited by 4
  30. 2014Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximationcited by 3
  31. 2017Stochastic Variational Inference for Bayesian Sparse Gaussian Process Regressioncited by 2
  32. 2021Convolutional Normalizing Flows for Deep Gaussian Processescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 1; 2025: 1; 2026: 2.

10 papers.

  1. 2022Sample-Then-Optimize Batch Neural Thompson Samplingcited by 25
  2. 2023Quantum Bayesian Optimizationcited by 12
  3. 2023Delayed Feedback in Kernel Banditscited by 10
  4. 2022Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraintscited by 9
  5. 2023Batch Bayesian Optimization for Replicable Experimental Designcited by 7
  6. 2023Training-Free Neural Active Learning with Initialization-Robustness Guaranteescited by 5
  7. 2024TS-RSR: A provably efficient approach for batch Bayesian Optimizationcited by 4
  8. 2025Lipschitz Bandits with Stochastic Delayed Feedbackcited by 1
  9. 2026Linear and Neural Dueling Bandits with Delayed Feedbackcited by 0
  10. 2026Improved Regret Analysis for Parallel Gaussian Process Bandit Optimizationcited by 0