English
Related papers

Related papers: Universality Laws for High-Dimensional Learning wi…

200 papers

Limit theorems are proved for quadratic forms of Gaussian random fields in presence of long memory. We obtain a non central limit theorem under a minimal integrability condition, which allows isotropic and anisotropic models. We apply our…

Statistics Theory · Mathematics 2010-01-08 Frédéric Lavancier , Anne Philippe

We study the fundamental problem of learning a marginally stable unknown nonlinear dynamical system. We describe an algorithm for this problem, based on the technique of spectral filtering, which learns a mapping from past observations to…

Machine Learning · Computer Science 2025-08-19 Evan Dogariu , Anand Brahmbhatt , Elad Hazan

One fundamental goal in any learning algorithm is to mitigate its risk for overfitting. Mathematically, this requires that the learning algorithm enjoys a small generalization risk, which is defined either in expectation or in probability.…

Machine Learning · Computer Science 2016-10-04 Ibrahim Alabdulmohsin

For a class of symmetric random matrices whose entries are martingale differences adapted to an increasing filtration, we prove that under a Lindeberg-like condition, the empirical spectral distribution behaves asymptotically similarly to a…

Probability · Mathematics 2014-02-27 Florence Merlevède , Costel Peligrad , Magda Peligrad

Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data. Toward addressing this challenge, we consider the domain generalization…

Machine Learning · Statistics 2021-11-16 Alexander Robey , George J. Pappas , Hamed Hassani

While nonlinear optical spectroscopy is becoming more commonly used to study the excited states of nonlinear-optical systems, a general theory of inhomogeneous broadening is rarely applied in lieu of either a simple Lorentzian or Gaussian…

Optics · Physics 2008-02-26 Robert J. Kruhlak , Mark G. Kuzyk

The central limit theorem provides the theoretical foundation for the universality of the normal distribution: under broad conditions, the asymptotic distribution of a sum of independent random variables approaches a Gaussian. Yet, physical…

Data Analysis, Statistics and Probability · Physics 2026-03-26 Mario Castro , José A. Cuesta

In this paper we provide explicit upper bounds on some distances between the (law of the) output of a random Gaussian NN and (the law of) a random Gaussian vector. Our results concern both shallow random Gaussian neural networks with…

This paper presents a novel framework of neural networks for isotropic hyperelasticity that enforces necessary physical and mathematical constraints while simultaneously satisfying the universal approximation theorem. The two key…

Computational Engineering, Finance, and Science · Computer Science 2026-05-19 Gian-Luca Geuken , Patrick Kurzeja , David Wiedemann , Jörn Mosler

Machine learning models are vulnerable to adversarial perturbations, and a thought-provoking paper by Bubeck and Sellke has analyzed this phenomenon through the lens of over-parameterization: interpolating smoothly the data requires…

Machine Learning · Statistics 2023-05-30 Simone Bombari , Shayan Kiyani , Marco Mondelli

We study universal traits which emerge both in real-world complex datasets, as well as in artificially generated ones. Our approach is to analogize data to a physical system and employ tools from statistical physics and Random Matrix Theory…

Machine Learning · Computer Science 2024-04-08 Noam Levi , Yaron Oz

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Machine Learning · Computer Science 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

In Selk and Gertheiss (2022) a nonparametric prediction method for models with multiple functional and categorical covariates is introduced. The dependent variable can be categorical (binary or multi-class) or continuous, thus both…

Statistics Theory · Mathematics 2023-04-04 Leonie Selk

Doubly stochastic learning algorithms are scalable kernel methods that perform very well in practice. However, their generalization properties are not well understood and their analysis is challenging since the corresponding learning…

Machine Learning · Statistics 2018-03-12 Junhong Lin , Lorenzo Rosasco

In this paper, we showed that the feature map of a convolution layer is equivalent to the unnormalized log posterior of a special kind of Gaussian mixture for image modeling. Then we expanded the model to drive diverse features and proposed…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Lifan Liang

This paper studies the generalization properties of a recently proposed kernel method, the Random Feature models with Learnable Activation Functions (RFLAF). By applying a data-dependent sampling scheme for generating features, we provide…

Machine Learning · Computer Science 2025-10-20 Zailin Ma , Jiansheng Yang , Yaodong Yang

We consider a general class of statistical experiments, in which an $n$-dimensional centered Gaussian random variable is observed and its covariance matrix is the parameter of interest. The covariance matrix is assumed to be…

Statistics Theory · Mathematics 2025-01-17 Cristina Butucea , Alexander Meister , Angelika Rohde

Via an overparameterized linear model with Gaussian features, we provide conditions for good generalization for multiclass classification of minimum-norm interpolating solutions in an asymptotic setting where both the number of underlying…

Machine Learning · Computer Science 2022-06-06 Vignesh Subramanian , Rahul Arya , Anant Sahai

In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…

Machine Learning · Computer Science 2022-09-30 Rudra P. K. Poudel , Harit Pandya , Roberto Cipolla

Asymptotic equivalence theory developed in the literature so far are only for bounded loss functions. This limits the potential applications of the theory because many commonly used loss functions in statistical inference are unbounded. In…

Statistics Theory · Mathematics 2009-09-03 T. Tony Cai , Harrison H. Zhou