stat.ML · 2026-07-10 · No. 49

Machine Learning, 2026-07-10.

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

    Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling

    Yiwei Zhou

    stat.ML · cs.LG · math.NA · math.PR

    Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small forward-marginal error does not guarantee numerical stability. We construct a single smooth score field with arbitrarily small forward-marginal $L^2$ error. The learned reverse-time process is nonexplosive, has moments of every order, and can be arbitrarily close to...

    arxiv.org/abs/2607.08757 · PDF

  2. 02

    High-Dimensional Procrustes Matching via Tree Counts

    Xiaochun Niu, Tselil Schramm, Jiaming Xu

    stat.ML · cs.IT · cs.LG · math.ST

    Suppose we observe two sets of $n$ Gaussian vectors in $\mathbb{R}^d$, with the promise that, after applying a permutation of $[n]$ and a rotation of $\mathbb{R}^d$, the two sets are $ρ$-correlated. The Procrustes matching problem asks us to recover the unknown permutation of $[n]$ that aligns the two sets. The problem is well-studied in the low-dimensional regime $d=O(\log n)$, but the high-dimensional regime $d\gg \log n$ has remained...

    arxiv.org/abs/2607.08538 · PDF

  3. 03

    Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning

    Zijie Cheng, Yang Peng, Zhihua Zhang

    stat.ML · cs.LG

    In this paper, we study quantile-based distributional reinforcement learning from the perspective of statistical efficiency. We focus on distributional policy evaluation, whose goal is to characterize the return distribution, namely the distribution of discounted cumulative rewards under a given policy. To obtain a finite-dimensional representation of the return distribution, we consider the quantile fixed point $η_m$ induced by the...

    arxiv.org/abs/2607.08444 · PDF

  4. 04

    Prediction-Powered Active Testing

    Kianoosh Ashouritaklimi, Valentin Kilian, Daolang Huang, Tom Rainforth, François Caron

    stat.ML · cs.LG

    Active testing provides a label--efficient approach to risk estimation by adaptively selecting which test points should be labelled. However, existing estimators fail to exploit the informative predictions of powerful black--box models, even though such predictions are increasingly available in settings where labels remain expensive. To address this, we propose \textbf{Prediction--Powered Active Testing (PPAT)}, a novel label--efficient risk...

    arxiv.org/abs/2607.08347 · PDF

  5. 05

    Bayesian Experimental Design via Score Matching

    Angus Phillips, Gavin Kerrigan, Tom Rainforth

    stat.ML · cs.LG

    Policy-based approaches to Bayesian experimental design (BED) allow the learning of deep policy networks that adaptively make intelligent design decisions based on previously collected data. However, the training of such policies is often held back by a fundamental challenge: the double intractability of the expected information gain (EIG). This necessitates expensive or complex approximations that restrict the effort one can invest in...

    arxiv.org/abs/2607.08335 · 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.