arXiv Statistics ML By Saksham Jain, Guillaume Braun, Masaaki Imaizumi

High-Dimensional Off-Policy Evaluation without Sample Splitting using an Onsager Correction

Read the original on arXiv Statistics ML →

The paper introduces an Onsager‑corrected, target‑policy‑weighted criterion that estimates the out‑of‑sample risk of a reward model trained on the full dataset using only its training data, thereby eliminating the need for sample splitting. This approach allows early stopping along a full‑data gradient‑descent trajectory and provides uniform consistency guarantees for neural networks under Gaussian contexts and single‑index rewards. The correction also yields a doubly robust policy‑value estimator that remains consistent even when reward‑model prediction error does not vanish, and experiments demonstrate reduced risk‑estimation error and improved reward‑model selection compared to held‑out baselines. whyItMatters":"By removing the need for sample splitting, the method enables more efficient use of data and improves the reliability of off‑policy evaluation and reward‑model selection in high‑dimensional settings."

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 Statistics ML.

arXiv AI
Oct 1

Revisiting scaling laws for reward optimization

The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.

By Ali Aouad, Aymane El Gadarri, Vivek F. Farias
arXiv Machine Learning
Oct 9

Amortized Off-Policy Evaluation for LLMs

The paper introduces PFN‑OPE, a prior‑data fitted network that performs amortized off‑policy evaluation (OPE) for large language models (LLMs). Unlike traditional OPE methods that must be retrained for each new logged dataset or reward definition, PFN‑OPE is pretrained once on a diverse set of contextual‑bandit tasks and can estimate value for any new logged dataset and target response in a single forward pass. Experiments on HelpSteer2 and UltraFeedback with Qwen, Llama, and Gemma policies show that PFN‑OPE reduces error by 2.0 to 9.3 times compared to the best baselines in reward‑shifted settings.

By Younwoo Choi, Leo Feng, Vincent Liu, Haanvid Lee
arXiv Machine Learning
6d ago

High Probability Risk Control for Online Policy Learning

The paper introduces a method for controlling risk in online policy learning, ensuring that an agent’s policy risk remains below a specified threshold at every round with high probability. It tackles the challenges posed by feedback covariate shift by proposing a permutation‑based weighted risk evaluator, efficiently approximated via the Sinkhorn algorithm, and a Gaussian bootstrap‑derived upper confidence bound for policy selection. Theoretical results guarantee low‑variance risk estimation and asymptotic high‑probability risk control, while empirical tests on contextual bandits, safe question answering, and medical claim filtering demonstrate maintained risk levels, lower risk than baselines, and reliable policy selection.

By Yihong Guo, Drew Prinster, Suchi Saria, Anqi Liu