mlsanityData to 14 Oct 2026

Bias-Robust Bayesian Optimization via Dueling Bandits

arXiv 2105.11802 ↗First posted 25 May 2021stat.ML cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueling bandit model. Then we propose a novel approach for dueling bandits based on information-directed sampling (IDS). Thereby, we obtain the first efficient kernelized algorithm for dueling bandits that comes with cumulative regret guarantees. Our analysis further generalizes a previously proposed semi-parametric linear bandit model to non-linear reward functions, and uncovers interesting links to doubly-robust estimation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 25 May 2021.

Builds on

21 of 42 references.

References · 21

  1. 2018A Tutorial on Bayesian Optimizationcited by 744
  2. 2017On Kernelized Multi-armed Banditscited by 352
  3. 2014Learning to Optimize via Information-Directed Samplingcited by 168
  4. 2015High Dimensional Bayesian Optimisation and Bandits via Additive Modelscited by 139
  5. 2018Stochastic bandits robust to adversarial corruptionscited by 119
  6. 2018Preference-based Online Learning with Dueling Bandits: A Surveycited by 102
  7. 2019Better Algorithms for Stochastic Bandits with Adversarial Corruptionscited by 92
  8. 2019Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspacescited by 73
  9. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  10. 2018Adversarially Robust Optimization with Gaussian Processescited by 62
  11. 2020Distributionally Robust Bayesian Optimizationcited by 61
  12. 2020Information Directed Sampling for Linear Partial Monitoringcited by 40
9 more
  1. 2017Multi-dueling Bandits with Dependent Armscited by 35
  2. 2020Corruption-Tolerant Gaussian Process Bandit Optimizationcited by 34
  3. 2020Asymptotically Optimal Information-Directed Samplingcited by 33
  4. 2019Stochastic Linear Optimization with Adversarial Corruptioncited by 24
  5. 2018Semiparametric Contextual Banditscited by 19
  6. 2019Zeroth Order Non-convex optimization with Dueling-Choice Banditscited by 11
  7. 2019Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Modelcited by 10
  8. 2017Correlational Dueling Bandits with Application to Clinical Treatment in Large Decision Spacescited by 6
  9. 2020Regret Minimization in Stochastic Contextual Dueling Banditscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 3; 2024: 3; 2025: 1.

11 papers.

  1. 2022Data-Driven Offline Decision-Making via Invariant Representation Learningcited by 31
  2. 2022Multi-Fidelity Bayesian Optimization with Unreliable Information Sourcescited by 18
  3. 2024Optimal Design for Human Preference Elicitationcited by 17
  4. 2023Robust and Conjugate Gaussian Process Regressioncited by 14
  5. 2023Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applicationscited by 12
  6. 2022A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Banditscited by 11
  7. 2024Bandits with Preference Feedback: A Stackelberg Game Perspectivecited by 7
  8. 2023Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learningcited by 6
  9. 2022Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budgetcited by 5
  10. 2024Regret Minimization via Saddle Point Optimizationcited by 2
  11. 2025Robust Bayesian Optimisation with Unbounded Corruptionscited by 1