stat.ML · 2026-09-28 · No. 127

Machine Learning, 2026-09-28.

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

    First-Order Stationarity of Reverse Diffusions

    Zhifeng Chen, Chenyang Jiang, Yazhen Wang

    stat.ML · cs.LG

    Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusions contract relative Fisher divergences at explicit exponential rates whenever the stationary potential of the forward process is strongly convex---a condition on the noising process one chooses, not on the...

    arxiv.org/abs/2609.31612 · PDF

  2. 02

    Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach

    Damiano Brigo, Raphaël Huser, Dan Leonte

    stat.ML · cs.LG · stat.AP · stat.CO · stat.OT

    Deep learning has substantially accelerated the calibration of complex stochastic-volatility models, but neural point calibration alone does not capture the uncertainty remaining after an implied-volatility (IV) surface has been observed. We develop a simulation-based inference framework for rough Heston (rHeston) calibration that learns the posterior distribution of the model parameters conditional on an IV surface. Using neural ratio...

    arxiv.org/abs/2609.31570 · PDF

  3. 03

    Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport

    Haixiang Sun, Andrew L. Liu

    stat.ML · cs.LG · math.OC

    Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ significantly from historical training data. In high-stakes applications, robustness often depends on rare cases that finite datasets fail to capture, making simple resampling or perturbation insufficient for stress scenario generation. Existing outlier synthesis methods typically rely on sparse...

    arxiv.org/abs/2609.31470 · PDF

  4. 04

    Nonparametric In-Context Learning under Growing Geometric Complexity: Minimax Optimality and Local Geometry-Adaptivity of Transformers

    Jaehee Seo, Jisu Kim

    stat.ML · cs.LG · math.ST

    Transformers have become a central architecture for in-context learning (ICL), particularly through their state-of-the-art performance in large language models. This success motivates understanding how transformers exploit task-relevant structure in geometrically heterogeneous data. However, existing nonparametric ICL theory has largely focused on Euclidean domains or single-manifold models. To address this gap, we study the prediction...

    arxiv.org/abs/2609.31458 · PDF

  5. 05

    Equation discovery with Bayesian tree-adjoining grammars

    Christopher A. Lindley, Nikolaos Dervilis, Keith Worden

    stat.ML · cs.LG · eess.SY · stat.CO

    Tree-Adjoining Grammars (TAGs) have recently been introduced to Nonlinear System Identification (NLSI) as a means of encoding an entire model class as a finite set of grammatical rules, from which candidate models are assembled as trees. Existing TAG-based identifiers rely on evolutionary optimisation and return point estimates of the model structure. This paper instead proposes the TAG framework within a Bayesian setting. A generative prior...

    arxiv.org/abs/2609.31368 · PDF

  6. 06

    Geometric Moment Contraction for Stochastic Nesterov Acceleration

    Wei Biao Wu

    stat.ML · cs.LG

    We study geometric moment contraction (GMC) of the constant-parameter stochastic Nesterov recursion \[ Y_k=Θ_k+β(Θ_k-Θ_{k-1}),\qquad Θ_{k+1}=Y_k-γG(Y_k,X_{k+1}). \] Under mean strong monotonicity and stochastic $L^p$ Lipschitz continuity, an explicit Perron comparison proves synchronous $L^p$ contraction when $βγL_p<(1-β)(1-q_{γ,p})$. This direct criterion includes infinite-variance gradients for $1<p<2$, but its small-step regime requires...

    arxiv.org/abs/2609.31303 · PDF

  7. 07

    Conformal Prediction under Exponential-Tilt Joint Shift

    Seungjin Choi

    stat.ML · cs.LG · stat.ME

    Conformal prediction can lose coverage when the data distribution changes after deployment. We study adaptation using labeled source data and unlabeled target inputs, allowing both the input distribution and its relationship with outcomes to change. We use Exponential Tilt Reweighting Alignment (ExTRA), introduced for classification by Maity et al. (2023), to estimate structured distribution shifts. We compare using its estimated weights in...

    arxiv.org/abs/2609.30886 · 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.