stat.ML · 2026-10-26 · No. 154
Machine Learning, 2026-10-26.
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-
01
Singular Geometry of Low-Rank Adaptation
Kamillo Ferry, Anthea Monod, Keisuke Yano
stat.ML · cs.LG
Low-rank adaptation (LoRA) is now a standard approach to parameter-efficient fine-tuning of large neural networks. Its low-rank factorization is inherently non-identifiable, making LoRA a singular statistical model whose learning complexity cannot be described by parameter dimension alone. We study this complexity using the real log canonical threshold (RLCT) from singular learning theory and how it depends on both the low-rank...
-
02
Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes
August Arnstad, Geir Olve Storvik, Filippo Pagani, Leiv Rønneberg
stat.ML · cs.LG · stat.CO
There is growing evidence that the performance of a neural network depends largely on a small subset of its weights, which are typically identified by training a dense network and pruning it afterwards. Within a Bayesian framework, pruning can be directly incorporated through a spike-and-slab prior, providing a proper treatment of the uncertainties involved, both with respect to pruning and to parameter uncertainty. In Bayesian neural...
-
03
Score-Preserving Continual Lasso under Task Shift
Jingyi Guo, Runze Li, Lingzhou Xue
stat.ML · cs.LG · math.ST
Continual learning (CL) aims to learn from sequential tasks while mitigating catastrophic forgetting when historical data are no longer accessible. We study continual learning for high-dimensional sparse linear regression, where $\ell_1$ regularization creates a difficulty absent from continual ridge regression: that recursively reusing an $\ell_1$-penalized estimator can propagate earlier shrinkage and accumulate regularization bias across...
-
04
Acquisition for Spherical-Linear Bayesian Optimization on the Cube
Nathan Wycoff
stat.ML · cs.LG · stat.CO
Recent work demonstrated that executing Bayesian Optimization (BO) using simply a linear surrogate with a clever transformation is enough to approximate the performance of the standard Gaussian-Process (GP) based version on high-dimensional test functions. When the decision region is a sphere, this strategy admits rapid exact acquisition. However, it is the unit cube we encounter most often in the BO literature, and in this setting a standard...
-
05
Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System
Alban Farchi, Marcin Chrust, Massimo Bonavita, Marc Bocquet, Wei Pan, Patrick Laloyaux
stat.ML · cs.LG
Hybrid forecasting systems combining machine learning and numerical weather prediction offer a promising route toward improved forecast skill while preserving physical consistency. In this study, we investigate online learning of state-dependent model-error corrections within the Integrated Forecasting System using 4D-Var. Building on previous work, we represent model error using a neural network embedded within the forecast model and trained...
-
06
Exact Global Minimax Risk near Nonidentification
Kaiyue Yang, Yunan Wu
stat.ML · cs.LG · math.ST
We study squared-error estimation when a nuisance parameter is unidentified on a submodel but affects a target that vanishes there. For models with higher-order profile expansions, we give sufficient conditions under which the largest critical-path minimax risk is the exact asymptotic minimax risk over the full parameter space. An efficient observable feature, negligible calibration error and stable recovery yield one estimator attaining the...
-
07
Empirical concentration for chains with infinite memory
Pierre Alquier, Paul Doukhan
stat.ML · cs.LG
Concentration inequalities for time series usually involve unknown quantities measuring dependence. This prevents their direct use as confidence bounds, or as criteria for learning algorithms. Recent works proved empirical concentration inequalities for stationary Markov chains, where the unknown quantities are estimated. We extend this approach beyond the Markov case, by considering stationary chains with infinite memory. We first establish...
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.