arXiv Machine Learning
Variance-Optimal Off-Policy Evaluation with Conjunct Effect Modeling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Oct 6
Variance-Optimal Off-Policy Evaluation with Conjunct Effect Modeling
Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly robust (DR) estimation remains unbiased under co...
arXiv AI
Oct 9
Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation
The paper proposes a method for allocating limited counterfactual annotation resources from multiple sources—such as domain experts and large language models—to improve off-policy evaluation in contextual bandits. By formulating an integer optimization problem that balances source-specific costs and error rates, the authors derive a majorization‑minimization algorithm that iteratively reduces estimator variance. Experiments on synthetic clinical and education bandit data demonstrate that the optimized allocation cuts mean‑squared error by over 20% compared to no annotation.
arXiv Machine Learning
Jun 2
Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation
arXiv:2509. 03456v2 Announce Type: replace-cross Abstract: Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits.
arXiv Machine Learning
Jun 29
Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits
arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.
arXiv Machine Learning
Jun 2
Bandit Simulation for Average Reward Inference
arXiv:2606. 00913v1 Announce Type: cross Abstract: Multi-arm bandit algorithms are increasingly used in online platforms, clinical trials, and social science experiments, but valid statistical inference on their performance remains an open challenge.
arXiv Machine Learning
Sep 30
Pointwise or Pairwise: When Do Pairwise Losses Help Reward Learning, Provably?
arXiv:2609.37209v1 Announce Type: new Abstract: Pairwise losses are increasingly used for reward learning even when pointwise rewards are observed, with mixed empirical results. When and why do pairw...