stat.ML · 2026-06-08 · No. 17

Machine Learning, 2026-06-08.

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

    Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions

    Raphael C Kim, Jingsen Zhu, Ramin Zabih, Michele Santacatterina

    stat.ML · cs.LG

    Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and...

    arxiv.org/abs/2606.07399 · PDF

  2. 02

    Deep Single-Index Fréchet Regression

    Muqing Cui, Yidong Zhou, Su I Iao, Hans-Georg Müller

    stat.ML · cs.LG

    Predicting outputs that are located in non-Euclidean spaces, such as probability distributions, networks, and symmetric positive-definite matrices, is becoming increasingly important in modern data analysis, particularly when inputs are high-dimensional. We propose DeSI (Deep Single-Index Fréchet Regression), a semiparametric framework for regression with metric space-valued outputs and multivariate inputs that assumes a single-index...

    arxiv.org/abs/2606.06957 · PDF

  3. 03

    Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments

    Qianqian Lei, Soham Bonnerjee, Yuefeng Han, Wei Biao Wu

    stat.ML · cs.LG · math.ST

    While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or sub-Gaussian/sub-Weibull tail assumptions, which can be overly restrictive for modern settings with heavy-tailed or unbounded losses. We develop a stability-based framework that requires only a finite $L_p$ moment condition. Our first contribution is sharp...

    arxiv.org/abs/2606.06855 · PDF

  4. 04

    The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces

    Soo Min Kwon, Alec S. Xu, Can Yaras, Dogyoon Song, Laura Balzano, Qing Qu

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

    The transformer's emergent ability to perform in-context learning (ICL) has sparked a wide range of studies designed to understand its underlying mechanisms. Existing works often study how training task diversity, defined either as the number of ICL training task vectors or as the number of function classes from which the task vectors are drawn, shapes both the learning dynamics and generalization capabilities of ICL. While both definitions...

    arxiv.org/abs/2606.06814 · PDF

  5. 05

    Empirical Transfer Operators and Finite-Sample Change Detection for Noisy Expanding Interval Maps

    Aparna Rajput

    stat.ML · cs.LG · math.DS

    We study finite-sample change detection for one-dimensional noisy dynamical systems using partition-based empirical approximations of stationary behaviour. Given observations from an interval-valued process, we partition the state space, estimate a finite transition matrix from observed transitions between partition elements, and apply a small Doeblin-type regularisation to ensure a unique stationary distribution. From an initial reference...

    arxiv.org/abs/2606.06785 · PDF

  6. 06

    Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

    Junyu Zhou, Puyu Wang, Yunwen Lei, Marius Kloft, Yiming Ying

    stat.ML · cs.AI · cs.LG

    Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory. While recent advances, particularly works under the Neural Tangent Kernel (NTK) regime, have shed light on the behavior of shallow architectures, the statistical generalization properties of deep neural networks (DNNs), especially in regression tasks, remain far less understood. In this paper, we make...

    arxiv.org/abs/2606.06772 · PDF

  7. 07

    Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks

    Junyu Zhou, Puyu Wang, Yunwen Lei, Yiming Ying, Ding-Xuan Zhou

    stat.ML · cs.AI · cs.LG

    Recent progress has been made in understanding the statistical generalization performance of gradient descent methods for overparameterized neural networks within the neural tangent kernel (NTK) regime. However, most of the existing work on regression problems is limited to shallow network architectures, leaving a notable gap in the theory of deep neural networks. This paper addresses this gap by presenting a comprehensive generalization...

    arxiv.org/abs/2606.06764 · 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.