mlsanityData to 14 Oct 2026

PAC-Bayesian Offline Contextual Bandits With Guarantees

arXiv 2210.13132 ↗First posted 24 Oct 2022stat.ML cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractable or loose bounds. We analyse the problem through the PAC-Bayesian lens, interpreting policies as mixtures of decision rules. This allows us to propose novel generalization bounds and provide tractable algorithms to optimize them. We prove that the derived bounds are tighter than their competitors, and can be optimized directly to confidently improve upon the logging policy offline. Our approach learns policies with guarantees, uses all available data and does not require tuning additional hyperparameters on held-out sets. We demonstrate through extensive experiments the effectiveness of our approach in providing performance guarantees in practical scenarios.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 21 of its 55 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

21 of 55 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 533
  4. 2021User-friendly introduction to PAC-Bayes boundscited by 239
  5. 2017EMNIST: an extension of MNIST to handwritten letterscited by 213
  6. 2018More Robust Doubly Robust Off-policy Evaluationcited by 141
  7. 2015Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challengescited by 114
  8. 2016Optimal and Adaptive Off-policy Evaluation in Contextual Banditscited by 111
  9. 2016Off-policy evaluation for slate recommendationcited by 103
  10. 2018Offline A/B testing for Recommender Systemscited by 96
  11. 2018Policy Evaluation and Optimization with Continuous Treatmentscited by 58
  12. 2018Variance reduction properties of the reparameterization trickcited by 41
9 more
  1. 2019Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networkscited by 38
  2. 2020Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weightingcited by 38
  3. 2018Bayesian Counterfactual Risk Minimizationcited by 28
  4. 2019Distributionally Robust Counterfactual Risk Minimizationcited by 26
  5. 2021Offline Neural Contextual Bandits: Pessimism, Optimization and Generalizationcited by 25
  6. 2020BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signalscited by 19
  7. 2019Imitation-Regularized Offline Learningcited by 17
  8. 2020Offline Contextual Bandits with Overparameterized Modelscited by 10
  9. 2020Improving Offline Contextual Bandits with Distributional Robustnesscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 4; 2025: 8; 2026: 2.

20 papers.

Sort:

By area:

  1. 2024Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learningcited by 16
  2. 2023Exponential Smoothing for Off-Policy Learningcited by 15
  3. 2023Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Banditscited by 15
  4. 2023Importance-Weighted Offline Learning Done Rightcited by 15
  5. 2023Learning via Wasserstein-Based High Probability Generalisation Boundscited by 12
  6. 2025Towards a Sharp Analysis of Offline Policy Learning for f-Divergence-Regularized Contextual Banditscited by 10
  7. 2024Diffusion Models Meet Contextual Banditscited by 5
  8. 2024Bayesian Off-Policy Evaluation and Learning for Large Action Spacescited by 5
  9. 2025Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezingcited by 4
  10. 2023Fast Slate Policy Optimization: Going Beyond Plackett-Lucecited by 3
  11. 2024Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Samplingcited by 3
  12. 2023Federated Learning with Nonvacuous Generalisation Boundscited by 2
8 more
  1. 2025Exploiting Similarities in A/B Testing with Off-Policy Estimationcited by 2
  2. 2025Experimental Design for Semiparametric Banditscited by 1
  3. 2025Non-Linear Counterfactual Aggregate Optimizationcited by 1
  4. 2025Offline Contextual Bandit with Counterfactual Sample Identificationcited by 1
  5. 2025Counterfactual Inference under Thompson Samplingcited by 0
  6. 2025Sequential Off-Policy Learning with Logarithmic Smoothingcited by 0
  7. 2026General Bayesian Policy Learningcited by 0
  8. 2026On-Policy and Off-Policy Learning for Large Action Spacescited by 0