stat.ML · 2026-09-03 · No. 104

Machine Learning, 2026-09-03.

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

    Full-Model Optimality for Tunable Linear Generative Priors in Compressed Sensing

    Zhaoming Li, Paul Hand

    stat.ML · cs.LG

    Generative models have been studied experimentally and theoretically as priors for inverse problems such as compressed sensing. Recent work by Gunn et al. studied the use of generative priors with tunable complexity, where a family of generative priors with varying complexity is maintained and a specific complexity can be selected at inversion time. They demonstrated that lower reconstruction errors can be experimentally attained for a...

    arxiv.org/abs/2609.02790 · PDF

  2. 02

    Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency

    Jia-Nan Wang, Zixun Huang, Kairui Li, Lei Wu

    stat.ML · cs.LG · math.OC

    We study when and how momentum improves large-batch training in the one-pass regime, using power-law kernel regression as a tractable setting. We first characterize risk stability through the critical learning rate, defined as the largest learning rate for stable training, and obtain $η_{\mathrm{SGD}}^{\mathrm{crit}}\eqsim 1$, $η_{\mathrm{Polyak}}^{\mathrm{crit}}\eqsim \min\{1,B(1-ρ)\}$, and $η_{\mathrm{Nesterov}}^{\mathrm{crit}}\eqsim...

    arxiv.org/abs/2609.02728 · PDF

  3. 03

    A computational approach to maximum likelihood thresholds for colored Gaussian graphical models

    Roser Homs, Olga Kuznetsova, Bernadette J. Stolz

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

    Gaussian graphical models (GGMs) are essential tools for interpretable structure learning. However, in high-dimensional, small-sample regimes, the available data is often insufficient for the maximum likelihood estimator to exist. Colored Gaussian graphical models (CGGMs) mitigate this limitation by imposing symmetry constraints through graph coloring, which reduces the required sample size. This minimal number of observations needed to...

    arxiv.org/abs/2609.02382 · PDF

  4. 04

    From topology learning to graph generation: A unifying perspective

    Xiaowen Dong, Hoi-To Wai, Siheng Chen, Laura Toni, Dorina Thanou

    stat.ML · cs.LG · eess.SP

    Learning graph structures from data is a fundamental problem that spans a wide range of signal processing and machine learning tasks. While significant effort has been made to tackle the problem, existing research has largely evolved along two parallel directions. The first seeks to infer the topology of an individual graph from observations supported on it, whereas the second seeks to learn a generative distribution from observed graph...

    arxiv.org/abs/2609.02286 · PDF

  5. 05

    Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation

    Shizhe Zhang, Mingyang Zhao, Lei Ma

    stat.ML · cs.AI · cs.LG

    Generative modeling directly on geometric manifolds can avoid errors introduced by flattening non-Euclidean data, repeated ambient projection, and coordinate inconsistency in Euclidean representations. Schrodinger bridges provide a probabilistic generative framework for entropy-regularized transport between prescribed endpoint distributions. We study Schrodinger bridges for kinetic dynamics on Lie group manifolds with state X_t = (g_t, xi_t)...

    arxiv.org/abs/2609.02196 · PDF

  6. 06

    HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC

    Ming Tan, Xiyun Jiao

    stat.ML · cs.LG · stat.CO

    Stochastic gradient Markov chain Monte Carlo (SGMCMC) methods enable scalable Bayesian inference, but their performance depends strongly on hyperparameters such as the step size, mini-batch size, and number of leapfrog steps. Since most SGMCMC algorithms lack a Metropolis-Hastings acceptance rate, standard acceptance-based tuning methods are not directly applicable. We propose HyperMC, a multi-fidelity tuning framework that combines...

    arxiv.org/abs/2609.02138 · PDF

  7. 07

    Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling

    Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya, Bani K. Mallick

    stat.ML · cs.IT · cs.LG · math.ST

    We study a variant of the Thompson Sampling (TS) algorithm, called $α$-TS, for solving stochastic generalized linear bandit problems. Existing analyses of TS require inflating the posterior variance to derive near-optimal regret guarantees. We formalize the idea of variance inflation by introducing $α$-TS that uses a fractional or $α$-posterior instead of the standard posterior. Our main contribution is to identify general regularity...

    arxiv.org/abs/2609.01999 · 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.