arXiv Machine Learning By Olivier Jeunen, Shashank Gupta

Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation

Read the original on arXiv Machine Learning →

arXiv:2602. 14914v3 Announce Type: replace Abstract: Off-policy evaluation (OPE) is essential for assessing ranking and recommendation systems without costly online interventions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Sep 1

Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior

The paper introduces Adaptive Doubly Robust (ADR), an off‑policy evaluation method for ranking policies that blends adaptive importance weighting with reward regression to reduce variance. ADR is unbiased when the true user behavior model is known and, under a sufficient condition, achieves lower variance than the prior Adaptive Inverse Propensity Scoring (AIPS) approach. Experiments on synthetic data show that ADR consistently improves mean squared error over AIPS and other ranking OPE estimators across various data sizes and ranking lengths.

By Kosuke Iguchi, Ren Kishimoto
arXiv Machine Learning
Oct 23

Doubly Robust Distributionally Robust Offline Contextual Pricing

The paper introduces a doubly robust framework for distributionally robust offline contextual pricing, addressing challenges of distributional shifts and continuous actions. It proposes a localized DR estimator that is computationally efficient and semiparametrically optimal, and a learning algorithm that exploits demand noise smoothness to achieve finite‑sample regret bounds of τ^{-σ/(2σ+1)} for smoothness orders s=1,2. Experiments across varying distribution shifts demonstrate the effectiveness of the proposed methods.

By Min Xu, Xinyi Yin, Yunfan Zhang, Yuxuan Han, Houcai Shen, Caihua Chen
arXiv Machine Learning
6d ago

Prediction-Powered LLM Ranking with Adaptively Collected Human Feedback

The paper introduces Prediction-Powered Ranking (PP‑Rank), a framework that blends large language model (LLM) judge predictions with limited human feedback to rank LLMs more precisely while maintaining valid inference under adaptive sampling. PP‑Rank uses data‑driven prediction weights to minimize asymptotic covariance, establishes asymptotic normality for general evaluation targets, and provides a rule for reducing exploration that balances cost and variance. Experiments on UltraFeedback‑Extended and synthetic data show that PP‑Rank improves score estimation, narrows confidence intervals, certifies rankings, and can cut evaluation costs without losing precision.

By Gabriel Sargent, Will Wei Sun, Zhengwu Zhang, Yufeng Liu