mlsanityData to 7 Oct 2026

Bayesian Counterfactual Risk Minimization

arXiv 1806.11500 ↗First posted 29 Jun 2018cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, potentially data-dependent, regularization technique for CRM. Experimental results indicate that this technique outperforms standard L2 regularization, and that it is competitive with variance regularization while being both simpler to implement and more computationally efficient.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 6; 2024: 5; 2025: 7; 2026: 3.

28 papers.

Sort:

By area:

  1. 2022PAC-Bayesian Offline Contextual Bandits With Guaranteescited by 19
  2. 2024Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learningcited by 16
  3. 2023Exponential Smoothing for Off-Policy Learningcited by 15
  4. 2023Importance-Weighted Offline Learning Done Rightcited by 15
  5. 2023Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Banditscited by 14
  6. 2023Tighter PAC-Bayes Bounds Through Coin-Bettingcited by 13
  7. 2024POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decompositioncited by 13
  8. 2023Marginal Density Ratio for Off-Policy Evaluation in Contextual Banditscited by 9
  9. 2025Towards a Sharp Analysis of Offline Policy Learning for f-Divergence-Regularized Contextual Banditscited by 9
  10. 2022PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparisoncited by 7
  11. 2022Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Banditscited by 6
  12. 2024Diffusion Models Meet Contextual Banditscited by 5
16 more
  1. 2024Bayesian Off-Policy Evaluation and Learning for Large Action Spacescited by 5
  2. 2022PAC-Bayesian Lifelong Learning For Multi-Armed Banditscited by 4
  3. 2022Fast Offline Policy Optimization for Large Scale Recommendationcited by 4
  4. 2022Boosted Off-Policy Learningcited by 3
  5. 2023Fast Slate Policy Optimization: Going Beyond Plackett-Lucecited by 3
  6. 2024Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Samplingcited by 3
  7. 2025Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezingcited by 3
  8. 2022Semi-supervised Batch Learning From Logged Datacited by 2
  9. 2025A General Framework for Off-Policy Learning with Partially-Observed Rewardcited by 1
  10. 2025Clustered KL-barycenter design for policy evaluationcited by 0
  11. 2025MultiScale Contextual Bandits for Long Term Objectivescited by 0
  12. 2025Sequential Off-Policy Learning with Logarithmic Smoothingcited by 0
  13. 2025Offline Contextual Bandit with Counterfactual Sample Identificationcited by 0
  14. 2026General Bayesian Policy Learningcited by 0
  15. 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQLcited by 0
  16. 2026Cross-Domain Off-Policy Evaluation and Learning for Contextual Banditscited by 0