stat.ML · 2026-10-27 · No. 155

Machine Learning, 2026-10-27.

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

01 — The papers

9 entries
  1. 01

    Model Selection for Off-Policy Evaluation via Pairwise Bellman Validation

    Lars van der Laan, Vasilis Syrgkanis, Nathan Kallus

    stat.ML · cs.LG · econ.EM

    Model selection and hyperparameter tuning pose a central challenge in off-policy evaluation (OPE) because errors of fitted Q-functions and occupancy-ratio estimates cannot be directly evaluated from held-out transitions. Bellman-residual and minimax validation methods often require auxiliary regressions or optimization over separate critic classes, adding computational and tuning costs. We introduce pairwise Bellman validation (PBV), a...

    arxiv.org/abs/2610.35748 · PDF

  2. 02

    Provably Efficient Q-learning for Robust Reinforcement Learning

    Yuchen Jiao, Gen Li

    stat.ML · cs.AI · cs.LG · math.ST

    Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on robust MDPs (RMDPs) have been proposed, for ensuring that agents can perform reliably to unpredictable conditions in real-world environments. Despite of the rich literature, \revision{an efficient model-free method is still lacking} for robust RL,...

    arxiv.org/abs/2610.35656 · PDF

  3. 03

    Depth Improves Training-Time Scaling for Difficult Tasks in Deep Linear Networks

    Taishi Watanabe, Ryo Karakida, Jun-nosuke Teramae

    stat.ML · cs.LG

    Neural scaling laws describe the predictable power-law dependence of model performance on training time, dataset size, and model scale, with the exponents quantifying how performance changes with resources. Recent theory has shown how scaling exponents are shaped by the data distribution and the structure of the learning task, but whether network depth can improve training-time scaling has remained unsettled. Through a refined analysis of...

    arxiv.org/abs/2610.35514 · PDF

  4. 04

    A knowledge-driven nonconvex square-root regularization framework for joint group sparsity and structured smoothness

    Wanling Xie, Hu Yang

    stat.ML · cs.LG · stat.CO

    Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural priors into the learning process. Among these priors, pre-defined grouped structure and piecewise smoothness are ubiquitous in real-world applications. However, most existing structured regularization methods are built on squared loss and convex penalties, rarely jointly model these two...

    arxiv.org/abs/2610.35428 · PDF

  5. 05

    Beyond Wasserstein Proximity: Finding Better Transfer Sources

    Gordei Verbii, Georgii Killinkarov, Vladimir Yafarov

    stat.ML · cs.LG

    Source selection often favors similar data, yet marginal proximity need not identify the most useful pretraining source. We motivate a conditional alternative through domain-adaptation theory and a regression example in which broader source variation improves estimation despite increasing Wasserstein distance. We examine five-day cryptocurrency volatility using ten Binance spot assets, six forecaster families, three seeds, and shared temporal...

    arxiv.org/abs/2610.35314 · PDF

  6. 06

    Temporal-Difference Calibration of Black-Box Simulators

    Min Zeng, Xin Wen, Xi Chen, Yichen Zhang, Wen-Xin Zhou

    stat.ML · cs.LG

    We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values. The calibration parameter is defined through Bellman orthogonality, recovering the physical parameter under correct simulator specification and yielding a near-optimal $L_2$ approximation of the policy value under misspecification. We propose...

    arxiv.org/abs/2610.35311 · PDF

  7. 07

    Identities, Not Pairs: Distribution-Free False-Accept Control for Embedding-Based Verification

    Salim Khazem

    stat.ML · cs.LG

    Embedding-based verification often calibrates a false-accept threshold from all impostor pairs among $m$ identities, although these pairs share identities. We characterize a worst-case limit: when hub identities score highly against a fraction $ρ$ of the population, a calibration-only threshold with marginal false-accept rate (FAR) at most $α$ under every identity-exchangeable law reaches the hub score on hub-free calibration sets with...

    arxiv.org/abs/2610.35277 · PDF

  8. 08

    Sequential versus fully conditional specification for tree-based synthesis of health data

    R{é}my Chapelle, Mohammed Sedki

    stat.ML · cs.LG

    Disseminating synthetic data in place of original ones is a promising way to enforce privacy while complying with open science principles, especially in the healthcare domain. To keep pace with the rate at which researchers collect such data, there is a need for fast and flexible synthesis procedures. A popular class of such procedures is based on models of conditional distributions induced by decision trees. Such models can be combined into...

    arxiv.org/abs/2610.35163 · PDF

  9. 09

    Macro Mondrian Conformal Risk Control

    Julien Combes, Jean-Francois Coeurjolly, Alexandre Dervill{é}

    stat.ML · cs.LG

    Conformal Risk Control (CRC) extends conformal prediction beyond the coverage setting to the control of general monotone loss functions, in a distribution-free and modelagnostic fashion. This makes it well-suited to problems with high-dimensional targets, such as the semantic segmentation task addressed in this work. However, CRC guarantees only marginal control, meaning that the risk is controlled on average over the data distribution. Under...

    arxiv.org/abs/2610.35035 · 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.