mlsanityData to 14 Oct 2026

Leveraging User-Triggered Supervision in Contextual Bandits

arXiv 2302.03784 ↗First posted 7 Feb 2023cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

We study contextual bandit (CB) problems, where the user can sometimes respond with the best action in a given context. Such an interaction arises, for example, in text prediction or autocompletion settings, where a poor suggestion is simply ignored and the user enters the desired text instead. Crucially, this extra feedback is user-triggered on only a subset of the contexts. We develop a new framework to leverage such signals, while being robust to their biased nature. We also augment standard CB algorithms to leverage the signal, and show improved regret guarantees for the resulting algorithms under a variety of conditions on the helpfulness of and bias inherent in this feedback.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

24 of 43 references.

References · 24

  1. 2018A Reductions Approach to Fair Classificationcited by 587
  2. 2014Taming the Monster: A Fast and Simple Algorithm for Contextual Banditscited by 201
  3. 2013Bandits with Knapsackscited by 164
  4. 2015Doubly Robust Policy Evaluation and Optimizationcited by 158
  5. 2016Corralling a Band of Bandit Algorithmscited by 100
  6. 2019Linear Stochastic Bandits Under Safety Constraintscited by 90
  7. 2014Bandits with concave rewards and convex knapsackscited by 83
  8. 2021Adapting to Misspecification in Contextual Banditscited by 81
  9. 2018Adversarial Bandits with Knapsackscited by 73
  10. 2020Stochastic Bandits with Linear Constraintscited by 68
  11. 2014Nonstochastic Multi-Armed Bandits with Graph-Structured Feedbackcited by 61
  12. 2016Conservative Banditscited by 59
12 more
  1. 2016Conservative Contextual Linear Banditscited by 57
  2. 2017Active Learning for Cost-Sensitive Classificationcited by 41
  3. 2019Safe Linear Thompson Sampling with Side Informationcited by 37
  4. 2015Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Banditscited by 29
  5. 2015Thompson Sampling for Budgeted Multi-armed Banditscited by 24
  6. 2021The Pareto Frontier of model selection for general Contextual Banditscited by 24
  7. 2019Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedbackcited by 21
  8. 2020Conservative Exploration in Reinforcement Learningcited by 20
  9. 2020Improved Algorithms for Conservative Exploration in Banditscited by 16
  10. 2021Pareto Optimal Model Selection in Linear Banditscited by 14
  11. 2021Bandit Algorithms for Precision Medicinecited by 12
  12. 2022Stochastic Conservative Contextual Linear Banditscited by 6

Built on by

Not cited yet.