English
Related papers

Related papers: Wide flat minima and optimal generalization in cla…

200 papers

The assumption of Gaussian or Gaussian mixture data has been extensively exploited in a long series of precise performance analyses of machine learning (ML) methods, on large datasets having comparably numerous samples and features. To…

Machine Learning · Statistics 2025-03-14 Xiaoyi Mai , Zhenyu Liao

Motivated by problems in data clustering, we establish general conditions under which families of nonparametric mixture models are identifiable, by introducing a novel framework involving clustering overfitted \emph{parametric} (i.e.…

Statistics Theory · Mathematics 2020-02-19 Bryon Aragam , Chen Dan , Eric P. Xing , Pradeep Ravikumar

Clustering is a pivotal challenge in unsupervised machine learning and is often investigated through the lens of mixture models. The optimal error rate for recovering cluster labels in Gaussian and sub-Gaussian mixture models involves ad…

Statistics Theory · Mathematics 2024-07-18 Maximilien Dreveton , Alperen Gözeten , Matthias Grossglauser , Patrick Thiran

While several papers have investigated computationally and statistically efficient methods for learning Gaussian mixtures, precise minimax bounds for their statistical performance as well as fundamental limits in high-dimensional settings…

Machine Learning · Statistics 2013-06-11 Martin Azizyan , Aarti Singh , Larry Wasserman

We investigate a clustering problem with data from a mixture of Gaussians that share a common but unknown, and potentially ill-conditioned, covariance matrix. We start by considering Gaussian mixtures with two equally-sized components and…

Machine Learning · Statistics 2021-11-30 Damek Davis , Mateo Díaz , Kaizheng Wang

We consider a high-dimensional mixture of two Gaussians in the noisy regime where even an oracle knowing the centers of the clusters misclassifies a small but finite fraction of the points. We provide a rigorous analysis of the…

Machine Learning · Statistics 2021-03-22 Francesca Mignacco , Florent Krzakala , Yue M. Lu , Lenka Zdeborová

The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient…

Disordered Systems and Neural Networks · Physics 2022-02-15 Carlo Baldassi , Clarissa Lauditi , Enrico M. Malatesta , Gabriele Perugini , Riccardo Zecchina

Bayesian nonparametric mixture models are widely used to cluster observations. However, one major drawback of the approach is that the estimated partition often presents unbalanced clusters' frequencies with only a few dominating clusters…

Methodology · Statistics 2026-02-03 Beatrice Franzolini , Giovanni Rebaudo

This article provides, through theoretical analysis, an in-depth understanding of the classification performance of the empirical risk minimization framework, in both ridge-regularized and unregularized cases, when high dimensional data are…

Machine Learning · Statistics 2020-11-26 Xiaoyi Mai , Zhenyu Liao

We consider the problem of approximating a general Gaussian location mixture by finite mixtures. The minimum order of finite mixtures that achieve a prescribed accuracy (measured by various $f$-divergences) is determined within constant…

Statistics Theory · Mathematics 2025-04-08 Yun Ma , Yihong Wu , Pengkun Yang

Generalized linear models (GLMs) arise in high-dimensional machine learning, statistics, communications and signal processing. In this paper we analyze GLMs when the data matrix is random, as relevant in problems such as compressed sensing,…

Information Theory · Computer Science 2019-04-01 Jean Barbier , Florent Krzakala , Nicolas Macris , Léo Miolane , Lenka Zdeborová

Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by…

Machine Learning · Statistics 2018-11-21 Lori A. Dalton , Marco E. Benalcázar , Edward R. Dougherty

We study the clustering task under anisotropic Gaussian Mixture Models where the covariance matrices from different clusters are unknown and are not necessarily the identical matrix. We characterize the dependence of signal-to-noise ratios…

Statistics Theory · Mathematics 2021-01-19 Xin Chen , Anderson Y. Zhang

For many applications, an ensemble of base classifiers is an effective solution. The tuning of its parameters(number of classes, amount of data on which each classifier is to be trained on, etc.) requires G, the generalization error of a…

This paper studies the problem of estimating the means $\pm\theta_{*}\in\mathbb{R}^{d}$ of a symmetric two-component Gaussian mixture $\delta_{*}\cdot N(\theta_{*},I)+(1-\delta_{*})\cdot N(-\theta_{*},I)$ where the weights $\delta_{*}$ and…

Statistics Theory · Mathematics 2021-03-30 Nir Weinberger , Guy Bresler

The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which…

Machine Learning · Computer Science 2022-03-31 Andrew Gordon Wilson , Pavel Izmailov

Recent literature generalization in deep learning has examined the relationship between the curvature of the loss function at minima and generalization, mainly in the context of overparameterized neural networks. A key observation is that…

Machine Learning · Computer Science 2025-10-01 Neta Shoham , Liron Mor-Yosef , Haim Avron

The use of a finite mixture of normal distributions in model-based clustering allows to capture non-Gaussian data clusters. However, identifying the clusters from the normal components is challenging and in general either achieved by…

Methodology · Statistics 2016-06-21 Gertraud Malsiner-Walli , Sylvia Frühwirth-Schnatter , Bettina Grün

Modern machine learning usually involves predictors in the overparameterised setting (number of trained parameters greater than dataset size), and their training yields not only good performance on training data, but also good…

Machine Learning · Statistics 2025-02-12 Maxime Haddouche , Paul Viallard , Umut Simsekli , Benjamin Guedj

This note examines the behavior of generalization capabilities - as defined by out-of-sample mean squared error (MSE) - of Linear Gaussian (with a fixed design matrix) and Linear Least Squares regression. Particularly, we consider a…

Statistics Theory · Mathematics 2021-09-21 Karthik Duraisamy