English
Related papers

Related papers: Asymptotic Behavior of Bayesian Generalization Err…

200 papers

We develop a new method for studying the asymptotics of symmetric polynomials of representation-theoretic origin as the number of variables tends to infinity. Several applications of our method are presented: We prove a number of theorems…

Representation Theory · Mathematics 2015-12-22 Vadim Gorin , Greta Panova

Information geometry provides a geometric approach to families of statistical models. The key geometric structures are the Fisher quadratic form and the Amari-Chentsov tensor. In statistics, the notion of sufficient statistic expresses the…

Statistics Theory · Mathematics 2015-05-27 Nihat Ay , Jürgen Jost , Hông Vân Lê , Lorenz Schwachhöfer

Motivated by applications to group synchronization and quadratic assignment on random data, we study a general problem of Bayesian inference of an unknown ``signal'' belonging to a high-dimensional compact group, given noisy pairwise…

Statistics Theory · Mathematics 2025-12-23 Kaylee Y. Yang , Timothy L. H. Wee , Zhou Fan

Incorporating group symmetries into neural networks has been a cornerstone of success in many AI-for-science applications. Diagonal groups of isometries, which describe the invariance under a simultaneous movement of multiple objects, arise…

Machine Learning · Computer Science 2025-08-29 Kevin Han Huang , Ni Zhan , Elif Ertekin , Peter Orbanz , Ryan P. Adams

Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good…

Machine Learning · Computer Science 2020-05-26 Wesley J. Maddox , Gregory Benton , Andrew Gordon Wilson

We introduce a new type of local and microlocal asymptotic analysis in algebras of generalized functions, based on the presheaf properties of those algebras and on the properties of their elements with respect to a regularizing parameter.…

Functional Analysis · Mathematics 2009-04-18 Antoine Delcroix , Michael Oberguggenberger , Jean-André Marti

Machine learning algorithms use error function minimization to fit a large set of parameters in a preexisting model. However, error minimization eventually leads to a memorization of the training dataset, losing the ability to generalize to…

Machine Learning · Computer Science 2018-03-16 Fernando Martin-Maroto , Gonzalo G. de Polavieja

Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic…

Machine Learning · Computer Science 2021-10-19 Vaishnavh Nagarajan , J. Zico Kolter

Recently, combinations of generative and Bayesian machine learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated…

Machine Learning · Computer Science 2024-11-21 Sebastian Bieringer , Sascha Diefenbacher , Gregor Kasieczka , Mathias Trabs

Reliably predicting nuclear properties across the entire chart of isotopes is important for applications ranging from nuclear astrophysics to superheavy science to nuclear technology. To this day, however, all the theoretical models that…

Nuclear Theory · Physics 2025-10-29 Aman Sharma , Nicolas Schunck , Kyle Wendt

We consider a linear mixed-effects model with a clustered structure, where the parameters are estimated using maximum likelihood (ML) based on possibly unbalanced data. Inference with this model is typically done based on asymptotic theory,…

Statistics Theory · Mathematics 2021-03-30 Chih-Hao Chang , Hsin-Cheng Huang , Ching-Kang Ing

This paper considers the problem of learning the parameters in Bayesian networks of discrete variables with known structure and hidden variables. Previous approaches in these settings typically use expectation maximization; when the network…

Machine Learning · Computer Science 2013-09-27 Yonatan Halpern , David Sontag

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

In Bayesian nonparametric inference, random discrete probability measures are commonly used as priors within hierarchical mixture models for density estimation and for inference on the clustering of the data. Recently, it has been shown…

Statistics Theory · Mathematics 2012-11-26 Stefano Favaro , Antonio Lijoi , Igor Prünster

We study the parameter estimation problem in mixture models with observational nonidentifiability: the full model (also containing hidden variables) is identifiable, but the marginal (observed) model is not. Hence global maxima of the…

Machine Learning · Statistics 2020-02-20 A. E. Allahverdyan

The selection of optimal designs for generalized linear mixed models is complicated by the fact that the Fisher information matrix, on which most optimality criteria depend, is computationally expensive to evaluate. Our focus is on the…

Methodology · Statistics 2015-09-22 Timothy W. Waite , David C. Woods

This paper explores the generalization characteristics of iterative learning algorithms with bounded updates for non-convex loss functions, employing information-theoretic techniques. Our key contribution is a novel bound for the…

Machine Learning · Computer Science 2023-10-17 Jingwen Fu , Nanning Zheng

For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features models and kernel machines, or multi-index models and…

Machine Learning · Statistics 2025-06-02 Jean Barbier , Francesco Camilli , Minh-Toan Nguyen , Mauro Pastore , Rudy Skerk

The Gaussian mixture model is widely used in unsupervised learning, owing to its simplicity and interpretability. However, a fundamental limitation of the classical Gaussian mixture model is that it forces each observation to belong to…

Machine Learning · Statistics 2026-04-27 Huan Qing

The predominance of machine learning models in many spheres of human activity has led to a growing demand for their transparency. The transparency of models makes it possible to discern some factors, such as security or non-discrimination.…

Machine Learning · Computer Science 2026-01-16 Niffa Cheick Oumar Diaby , Thierry Duchesne , Mario Marchand