stat.ML · 2026-08-30 · No. 100

Machine Learning, 2026-08-30.

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

01 — The papers

7 entries
  1. 01

    A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning

    Zijie Cheng, Xiang Li, Yang Peng, Zhihua Zhang

    stat.ML · cs.LG

    We establish a global finite-sample guarantee for synchronous quantile temporal-difference learning (QTD) in tabular distributional reinforcement learning. The proof separates two stability mechanisms. A global comparison argument, based on the order monotonicity of reward cumulative distribution functions and the $W_\infty$ contraction of the distributional Bellman operator, brings an arbitrarily initialized iterate into a local...

    arxiv.org/abs/2608.27313 · PDF

  2. 02

    Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach

    Elena Badillo-Goicoechea, Fengfeng He

    stat.ML · cs.LG

    Music recommendation relies primarily on two signals: user-item interactions, which fail in the cold-start regime, and intrinsic musical content, available for any recording. We argue that a third, largely untapped signal is both richer and more principled: critical adjacency, the pairwise relation established when an expert critic explicitly links two artists in long-form prose. It encodes deliberate judgments about which artists belong...

    arxiv.org/abs/2608.27291 · PDF

  3. 03

    Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors

    Jitao Xu, Nobuo Sato, Yaohang Li

    stat.ML · cs.AI · cs.LG

    Many scientific and engineering applications require estimating unknown parameters from experimentally observable data -- an inverse problem that is inherently challenging due to nonlinearity, noise, and ill-posedness. In this paper, we propose an active diffusion-based inverse problem solver. A DM is trained to learn the mapping between the parameter space and the observable space. By iteratively detecting and correcting model...

    arxiv.org/abs/2608.27080 · PDF

  4. 04

    Representation Measurements Under Function-Preserving Reparameterizations

    Abdullah Karasan

    stat.ML · cs.LG

    Hidden coordinates are not uniquely determined by a language model's input--output function, so representation-derived measurements should be invariant to function-preserving changes of basis. This study shows that column-permutation parallel analysis violates function-preserving reparameterization invariance because its reference distribution and selected component count can change while the model function and observed covariance spectrum...

    arxiv.org/abs/2608.27020 · PDF

  5. 05

    Why not to use the Gaussian kernel

    Toni Karvonen, Chris J. Oates

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

    Kernels measure similarity or correlation in tasks such as regression and classification. The Gaussian kernel, other names of which include squared exponential and radial basis function kernel, is one of the most popular in Gaussian process regression. We argue that the Gaussian kernel is best avoided and should never be used as a default. The argument rests on two results demonstrating that the Gaussian kernel is extremely brittle. First,...

    arxiv.org/abs/2608.26974 · PDF

  6. 06

    Incremental Recommendation via Causal Models

    Athanasios Vlontzos, David Gustafsson, Michael O'Riordan, Ciarán M. Gilligan-Lee

    stat.ML · cs.LG · stat.ME

    Recommendation impressions are a finite resource, hence delivering a recommendation to a user who would discover the content organically yields no incremental value and displaces other recommendations that could. We address this by extending an existing production recommendation model to a causal architecture using holdback data that is already collected as part of routine experimentation infrastructure, requiring no new data collection. A...

    arxiv.org/abs/2608.26804 · PDF

  7. 07

    A Unified Descriptive-Complexity Framework for Model Selection under Correlated Designs

    Yanhang Zhang, Wei Liu, Yuhong Yang

    stat.ML · cs.LG

    Model selection becomes particularly challenging under strong predictor dependence and model-class uncertainty, especially when there are exponentially many models. We propose a Descriptive-Complexity Information Criterion (DCIC) that regularizes large candidate model collections through Kraft-admissible code lengths. Under sub-Weibull noise, we establish selection consistency through approximation-error separation without relying on RIP-type...

    arxiv.org/abs/2608.26618 · 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.