Conditionally Risk-Averse Contextual Bandits
Not on the map. Why?
Abstract (arXiv)
Contextual bandits with average-case statistical guarantees are inadequate in risk-averse situations because they might trade off degraded worst-case behaviour for better average performance. Designing a risk-averse contextual bandit is challenging because exploration is necessary but risk-aversion is sensitive to the entire distribution of rewards; nonetheless we exhibit the first risk-averse contextual bandit algorithm with an online regret guarantee. We conduct experiments from diverse scenarios where worst-case outcomes should be avoided, from dynamic pricing, inventory management, and self-tuning software; including a production exascale data processing system.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 62 references that are in the map. First posted on arXiv 24 Oct 2022.
Builds on
23 of 62 references.
References · 23
- 2014OpenML: networked science in machine learningcited by 523
- 2021The Statistical Complexity of Interactive Decision Makingcited by 208
- 2020Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oraclescited by 195
- 2020Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizabilitycited by 114
- 2016Corralling a Band of Bandit Algorithmscited by 99
- 2021Adapting to Misspecification in Contextual Banditscited by 81
- 2020Bao: Learning to Steer Query Optimizerscited by 62
- 2021Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discriminationcited by 53
- 2014Resourceful Contextual Banditscited by 45
- 2019A Survey on Practical Applications of Multi-Armed and Contextual Banditscited by 44
- 2022Contextual Bandits with Large Action Spaces: Made Practicalcited by 32
- 2021Off-Policy Risk Assessment in Contextual Banditscited by 29
11 more
- 2015Of Quantiles and Expectiles: Consistent Scoring Functions, Choquet Representations, and Forecast Rankingscited by 28
- 2019Sequential estimation of quantiles with applications to A/B-testing and best-arm identificationcited by 27
- 2020Thompson Sampling Algorithms for Mean-Variance Banditscited by 27
- 2020Optimal Thompson Sampling strategies for support-aware CVaR banditscited by 26
- 2016Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measurecited by 20
- 2022Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spacescited by 17
- 2018Risk-Averse Stochastic Convex Banditcited by 13
- 2020Risk-Constrained Thompson Sampling for CVaR Banditscited by 10
- 2020Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Schemecited by 9
- 2019X-Armed Bandits: Optimizing Quantiles, CVaR and Other Riskscited by 7
- 2022Risk-aware linear bandits with convex losscited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.