stat.ML · 2026-09-18 · No. 117

Machine Learning, 2026-09-18.

5 new papers in stat.ML. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

5 entries
  1. 01

    Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation

    Sho Kawano, Zehang Richard Li, Paul A. Parker

    stat.ML · cs.AI · cs.LG · stat.AP · stat.ME

    Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents. Exhaustive testing is expensive, so evaluation rests on a sample of labeled units. We treat the evaluation set as a finite population and seek accurate point and interval estimates of each domain mean. Direct estimators, including prediction-powered inference (PPI), use only a...

    arxiv.org/abs/2609.20758 · PDF

  2. 02

    TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models

    Jingbo Liu, Zhiyuan Yu

    stat.ML · cs.LG

    We study the Bayes-optimal spherical linear model as the ambient dimension and sample size grow proportionally, under a quantitative Marchenko--Pastur spectral-regularity condition on the design. This condition is satisfied by normalized i.i.d. designs with standardized entries of finite fourth moment, but does not require entrywise independence or impose conditions on the singular vectors. Under this condition, we prove a quantitative...

    arxiv.org/abs/2609.20577 · PDF

  3. 03

    Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs

    Zhenlin Yao, Wei Xiong

    stat.ML · cs.LG · stat.CO

    Accurate optimization of a supervised spectral objective need not produce an accurate population subspace or a better predictive representation. We investigate these distinctions for Online Kernel Supervised Principal Component Analysis (OKSPCA), which combines a centered cross-moment in finite random-feature coordinates with an Adam-style orthonormal basis update for an established objective. Fixed-map consistency, concentration and...

    arxiv.org/abs/2609.20454 · PDF

  4. 04

    Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning

    Weiwei Wang, Yuqiang Li, Xianyi Wu, Bingyi Jing

    stat.ML · cs.LG

    Offline policy evaluation (OPE) is crucial in high-stakes reinforcement learning applications, where new policies must be assessed reliably before deployment. In such settings, point estimates alone are insufficient; principled uncertainty quantification, such as confidence intervals and variance estimates, is essential for safe and risk-aware decision-making. A comprehensive way to unify these tasks is to estimate the sampling distribution...

    arxiv.org/abs/2609.20389 · PDF

  5. 05

    Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks

    Xianjun Li, Yunfei Yang

    stat.ML · cs.LG

    Recent studies have shown that smooth functions can be well approximated by ReLU neural networks with path norm constraint on the weights. We extend these results from uniform approximation to approximation in Sobolev norm. Specifically, we analyze how well Sobolev functions in $W^{n,p}$ can be approximated by neural networks with width $W$, depth $L$ and path norm bounded by $K$, when the approximation error is measured in the...

    arxiv.org/abs/2609.19937 · PDF

This edition is part of The Daily Abstract — stat.ML archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.