stat.ML · 2026-08-31 · No. 101

Machine Learning, 2026-08-31.

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

01 — The papers

4 entries
  1. 01

    Learning between the peaks: sharp asymptotics for kernel ridge regression under power-law anisotropy

    Lorenzo Rizzi, Arie Wortsman Zurich, Bruno Loureiro

    stat.ML · cs.LG

    We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent $α\geq 0$ for polynomial inner-product kernels. We derive asymptotically sharp expressions for the kernel spectrum and the generalization error in the polynomial high-dimensional regime $n=Θ(d^κ)$, revealing how anisotropy reshapes the learning curves. For weak anisotropy ($0<α<1$), the problem remains effectively...

    arxiv.org/abs/2608.28564 · PDF

  2. 02

    Localizing Global Discrepancies: Marginal Contributions and Contextual Anomaly Detection

    Tommaso dorigo

    stat.ML · cs.LG · physics.data-an

    Global goodness-of-fit and discrepancy statistics can establish that a sample departs from a reference distribution without identifying which observations drive the departure. We develop a framework for this localization problem by assigning to each observation its conditional or marginal contribution across random statistical contexts. This connects resampling diagnostics and data valuation to projection theory and event-level anomaly...

    arxiv.org/abs/2608.28375 · PDF

  3. 03

    I-FLOP: Fast Learning of Order and Parents from Interventional Data

    Liuting Chen, Alex Markham

    stat.ML · cs.LG

    We extend the FLOP (fast learning of order and parents) algorithm recently proposed by Wienöbst et al. (2026) from observational to interventional data. In particular, we use the interventional BIC score of Hauser and Bühlmann (2012), adapting it to be used with the iterative Cholesky-based score updates that are partly responsible for FLOP's speed. We show that, in the sample limit, I-FLOP recovers a DAG in the same interventional Markov...

    arxiv.org/abs/2608.28245 · PDF

  4. 04

    Conformal Risk-Averse Decision Making with Optimized Certainty Equivalent Risk Control

    Amirmohammad Farzaneh, Osvaldo Simeone

    stat.ML · cs.AI · cs.IT · cs.LG

    We study risk-averse decision making, in which an agent selects actions while being uncertain about the true system state. The risk is measured via optimized certainty equivalent (OCE) metrics, which generalize popular criteria such as mean-variance risk and conditional value-at-risk (CVaR). We characterize the optimal policy under known distributions, and show that it reduces to a prediction set-based solution for the CVaR. This provides an...

    arxiv.org/abs/2608.28179 · 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.