stat.ML · 2026-08-19 · No. 89
Machine Learning, 2026-08-19.
8 new papers in stat.ML. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Where A Small Language Model Helps in Invoice Categorisation, Understood Through Embedding Geometry
Emma Ceccherini, Daniel Lawson, Anjulika Salhan
stat.ML · cs.LG
Categorising invoices into the correct General Ledger (GL) code underpins financial reporting and tax compliance. This is a skilled accounting judgement rather than a routine task: the correct category depends subtly on the nature of the purchasing business, the vendor and the invoice text. Whilst AI is increasingly being adopted across industries to automate tasks, including invoice categorisation, implementations built on in-house small...
-
02
Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits
Kaifei Wang, Yinyu Ye, Han Zhong
stat.ML · cs.LG · math.OC · math.ST
Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-case regret $\mathcal{R}_{K,T}$ and instability $\mathcal S_{K,T}$, defined as the largest standard deviation of a terminal pull count, for $K$ arms and $T$ rounds. We prove the finite-time lower bound $\mathcal R_{K,T}\mathcal S_{K,T}\ge C T^{3/2}$, where $C$ is...
-
03
Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and a Tight Univariate Rate
Huibo Xu, Shi Fu, Qixin Zhang, Dacheng Tao
stat.ML · cs.LG · stat.AP
In high-dimensional online prediction, the best predictor may depend on only a few features, so regret should scale with sparsity rather than the ambient dimension. Feature priming pursues this goal by estimating feature weights from past data and refitting a minimum-norm predictor on the rescaled design. Warmuth and Amid asked at COLT 2023 whether any of three such rules admits a competitive online regret guarantee. Using the natural...
-
04
Online Generalized Sparse Regression: How Does Overparametrization Help?
Shuoguang Yang, Qiang Sun
stat.ML · cs.LG · math.ST
Regularized sparse regression has been extensively studied in the offline setting, but online formulation remains relatively under-explored. This gap stems from four key challenges: (i) the infeasibility of dynamically updating the regularization parameter in every online round, (ii) managing storage and memory complexity, (iii) enabling real-time computation via closed-form updates rather than solving full optimization problems at each...
-
05
Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines
Kaiji Sekimoto, Muneki Yasuda
stat.ML · cond-mat.dis-nn · cs.LG
Learning restricted Boltzmann machines (RBMs) is computationally challenging because it requires expectations whose exact evaluation is generally intractable. The expectations are typically evaluated using a sampling approximation based on blocked Gibbs sampling (BGS), which is a local Markov chain Monte Carlo transition kernel. However, the locality of BGS can lead to poor sampling quality when the RBM has high energy barriers, thereby...
-
06
SPACE: Sample-cloud Predictive Adaptive Conformal Ellipsoids for Multivariate Time-Series Forecasting
Baishi Li, Kelvin J. L. Koa, Ke-Wei Huang
stat.ML · cs.AI · cs.LG
Modern probabilistic time-series forecasters often express uncertainty through forecast samples. While typically converted into nominal prediction regions using empirical quantiles, these model-implied sets lack formal coverage guarantees and frequently deviate from nominal targets under distribution shift. Existing multivariate conformal methods can calibrate these regions online, but they typically estimate geometry from historical...
-
07
Expressivity In Multimodal Contrastive Learning
Andrew Stuart, Florian Wolf
stat.ML · cs.LG · math.ST
Contrastive learning has become a cornerstone of modern representation learning, powering CLIP-style models that underpin text-to-image generation, vision-language models, and retrieval across a rapidly growing range of modalities. Despite this empirical success, the expressive power of these architectures remains poorly understood. To gain insight, we study expressivity by adopting a population-level, density-estimation viewpoint: each...
-
08
Policy Optimization and Statistical Inference for Online Contextual Matrix Games
Liner Xiang, Yixin Wang, Hengrui Cai
stat.ML · cs.LG · math.ST · stat.ME
Online decision making often requires navigating a landscape shaped by both dynamic contexts and strategic interactions. In competitive pricing, for example, hotels must account for both dynamic contextual factors and rivals' strategic responses. Existing approaches address only part of this challenge: contextual bandits optimize single-agent decisions using observable features but ignore multi-player interactions, while online matrix games...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.