stat.ML · 2026-11-03 · No. 162

Machine Learning, 2026-11-03.

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

    Error Accumulation in Second-Order Sequential Machine Unlearning

    Chen Shang, Haolin Zou, Binghe Zhu, Arian Maleki

    stat.ML · cs.LG

    Machine unlearning seeks to remove the influence of deleted training data without full retraining. In the sequential setting, deletion requests arrive over time, and repeated updates can accumulate approximation errors. In this paper, we study error accumulation in high dimensions, where parameter count $p$ is proportional to sample size $n$, for second-order unlearning methods under two privacy settings: (i) \emph{partial unlearning}, which...

    arxiv.org/abs/2611.03445 · PDF

  2. 02

    Subpolynomial-Query Proximal Sampling Beyond Log-Concavity

    Wei Guo, Bo Yuan, Ye He, Jiaming Liang, Molei Tao, Yongxin Chen

    stat.ML · cs.CC · cs.LG · math.ST

    We study the gradient query complexity of sampling from a density $π(x)\propto\mathrm{e}^{-V(x)}$ on $\mathbb{R}^d$, where $V$ has a $β$-Lipschitz gradient but need not be convex. Our approach uses the proximal sampler, which alternates Gaussian perturbation with sampling a position conditional on the noisy observation. We implement its observation chain using the high-order noisy conditional sampler of [OpenAI 2026], obtaining improved...

    arxiv.org/abs/2611.03442 · PDF

  3. 03

    Neural Actor--Critic Learning with Minimax Critics and Reflected Langevin Sampling

    Kunqi Huang, Lican Kang, Hongrui Shu, Jincheng Ying

    stat.ML · cs.LG

    Actor--critic methods rely on critic gradients to improve continuous-action policies, yet finite-sample guarantees must control both value and gradient errors and their propagation through the actor. We develop a neural actor-critic procedure that combines a regularized minimax Bellman estimator over sigmoid networks with a finite reflected Langevin sampler driven by the fitted critic gradient. Under uniform Bellman regularity and covered...

    arxiv.org/abs/2611.03352 · PDF

  4. 04

    EventGPT: Next-Event Pretraining on Banking Customer Histories

    Denis Burakov

    stat.ML · cs.LG · q-fin.ST

    A model pretrained to predict a customer's next event can estimate the probability of future events without training on their labels and provide a reusable representation for supervised downstream banking tasks. We pretrain EventGPT, a hierarchical causal transformer, by next-token maximum likelihood estimation on the public Multimodal Banking Dataset (MBD-mini: 100,224 clients, 38.8 million transactions and 66.3 million geolocation pings)....

    arxiv.org/abs/2611.03302 · PDF

  5. 05

    Poisson Super Learning For Survival And Competing Risks On A Discretized Time Scale

    Gabriele Pittarello, Thomas Gerds, Pernille Falberg Rønn, Helene Charlotte Rytgaard

    stat.ML · cs.LG · stat.CO

    We introduce the Poisson Super Learner, a scalable ensemble method for survival and competing risks prediction with right-censored data. The approach exploits the correspondence between the likelihood of piecewise-constant hazard models and the Poisson likelihood. After expanding the data over a chosen time partition, candidate hazard learners are trained under a common Poisson loss, and cross-validated log-hazard predictions are combined by...

    arxiv.org/abs/2611.03256 · PDF

  6. 06

    Causal discovery needs explicit epistemic standards

    Harald Kugler, Leonard Henckel, Sebastian Weichwald

    stat.ML · cs.LG · stat.ME

    There are many causal discovery algorithms, but few guiding principles for choosing between them. Methods are usually compared through three lenses: identifiability, consistency, and benchmarks. Each introduces assumptions about the data-generating process that are often untestable. We argue that there are no shared standards for comparing, prioritizing, or even discussing those assumptions. We support this claim by showing that (i)...

    arxiv.org/abs/2611.03166 · PDF

  7. 07

    Specification-Aware Predictive Uncertainty Decomposition

    Roman Vashurin, Mikhail Seleznyov, Assel Yermekova, Fedor Chernogorskii, Danila Zykov, Elena Tutubalina, Alexander...

    stat.ML · cs.AI · cs.CL · cs.LG

    Classical decompositions of predictive uncertainty, such as the information-theoretic one, are defined for a fixed representation $x$ of the input object. They do not consider that $x$ may be incomplete, nor do they measure how much the missing information can affect the prediction. In Large Language Models, users can clarify an underspecified input without any retraining. The clarified input can describe the user's unobserved intent $z^*$...

    arxiv.org/abs/2611.02956 · 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.