mlsanityData to 7 Oct 2026

Online Decision Deferral under Budget Constraints

arXiv 2409.20489 ↗First posted 30 Sep 2024cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) models are increasingly used to support or substitute decision making. In applications where skilled experts are a limited resource, it is crucial to reduce their burden and automate decisions when the performance of an ML model is at least of equal quality. However, models are often pre-trained and fixed, while tasks arrive sequentially and their distribution may shift. In that case, the respective performance of the decision makers may change, and the deferral algorithm must remain adaptive. We propose a contextual bandit model of this online decision making problem. Our framework includes budget constraints and different types of partial feedback models. Beyond the theoretical guarantees of our algorithm, we propose efficient extensions that achieve remarkable performance on real-world datasets.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

20 of 35 references.

References · 20

  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 228
  3. 2013Bandits with Knapsackscited by 163
  4. 2019The Algorithmic Automation Problem: Prediction, Triage, and Human Effortcited by 101
  5. 2014Bandits with concave rewards and convex knapsackscited by 83
  6. 2015Linear Contextual Bandits with Knapsackscited by 82
  7. 2021Differentiable Learning Under Triagecited by 74
  8. 2018Adversarial Bandits with Knapsackscited by 73
  9. 2022Calibrated Learning to Defer with One-vs-All Classifierscited by 68
  10. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 68
  11. 2022Sample Efficient Learning of Predictors that Complement Humanscited by 46
  12. 2021Human-AI Collaboration with Bandit Feedbackcited by 36
8 more
  1. 2022Non-stationary Bandits with Knapsackscited by 25
  2. 2016An optimal algorithm for bandit convex optimizationcited by 20
  3. 2020A Bandit Model for Human-Machine Decision Making with Private Information and Opacitycited by 10
  4. 2021Learning-to-defer for sequential medical decision-making under uncertaintycited by 10
  5. 2023A Second-Order Method for Stochastic Bandit Convex Optimisationcited by 10
  6. 2019ROI Maximization in Stochastic Online Decision-Makingcited by 3
  7. 2022Contextual Bandits with Knapsacks for a Conversion Modelcited by 3
  8. 2024A Dynamic Model of Performative Human-ML Collaboration: Theory and Empirical Evidencecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Budgeted Multiple-Expert Deferralcited by 11
  2. 2025Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdowncited by 4
  3. 2026Online Learning-to-Defer with Varying Expertscited by 0
  4. 2026Learning to Assign Prediction Tasks to Agents with Capacity Constraintscited by 0
  5. 2026PixSim: a calibrated open-source simulator of instant-payment fraud, recovery and interdiction under analyst capacity constraintscited by 0