English
Related papers

Related papers: Surprises in High-Dimensional Ridgeless Least Squa…

200 papers

We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight…

Machine Learning · Statistics 2023-11-13 Jiyoung Park , Ian Pelakh , Stephan Wojtowytsch

Modern neural networks are often operated in a strongly overparametrized regime: they comprise so many parameters that they can interpolate the training set, even if actual labels are replaced by purely random ones. Despite this, they…

Machine Learning · Statistics 2022-06-10 Andrea Montanari , Yiqiao Zhong

Overparametrized neural networks tend to perfectly fit noisy training data yet generalize well on test data. Inspired by this empirical observation, recent work has sought to understand this phenomenon of benign overfitting or harmless…

Machine Learning · Statistics 2022-02-23 Andrew D. McRae , Santhosh Karnik , Mark A. Davenport , Vidya Muthukumar

We study the convergence of gradient methods for the training of mean-field single-hidden-layer neural networks with square loss. For this high-dimensional and non-convex optimization problem, most known convergence results are either…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

We study distributed learning with the least squares regularization scheme in a reproducing kernel Hilbert space (RKHS). By a divide-and-conquer approach, the algorithm partitions a data set into disjoint data subsets, applies the least…

Machine Learning · Computer Science 2017-03-14 Shao-Bo Lin , Xin Guo , Ding-Xuan Zhou

We study the properties of nonparametric least squares regression using deep neural networks. We derive non-asymptotic upper bounds for the prediction error of the empirical risk minimizer of feedforward deep neural regression. Our error…

Statistics Theory · Mathematics 2023-01-18 Yuling Jiao , Guohao Shen , Yuanyuan Lin , Jian Huang

Modern deep learning has revealed a surprising statistical phenomenon known as benign overfitting, with high-dimensional linear regression being a prominent example. This paper contributes to ongoing research on the ordinary least squares…

Statistics Theory · Mathematics 2024-11-12 Letian Yang , Dennis Shen

In functional linear regression, the parameters estimation involves solving a non necessarily well-posed problem and it has points of contact with a range of methodologies, including statistical smoothing, deconvolution and projection on…

Statistics Theory · Mathematics 2018-01-04 Andrea Ghiglietti , Francesca Ieva , Anna Maria Paganoni , Giacomo Aletti

We propose a novel algorithm for greedy forward feature selection for regularized least-squares (RLS) regression and classification, also known as the least-squares support vector machine or ridge regression. The algorithm, which we call…

Machine Learning · Statistics 2010-03-19 Tapio Pahikkala , Antti Airola , Tapio Salakoski

Additive regression models are actively researched in the statistical field because of their usefulness in the analysis of responses determined by non-linear relationships with multivariate predictors. In this kind of statistical models,…

Methodology · Statistics 2018-04-10 German A. Schnaidt Grez , Brani Vidakovic

Statistical inverse learning aims at recovering an unknown function $f$ from randomly scattered and possibly noisy point evaluations of another function $g$, connected to $f$ via an ill-posed mathematical model. In this paper we blend…

Statistics Theory · Mathematics 2024-01-22 Tapio Helin

The standard estimator for the two-point function of a homogeneous and isotropic random field is a special case of a larger class of least squares estimators that interpolate the function values. Using a different interpolation scheme,…

Instrumentation and Methods for Astrophysics · Physics 2018-08-17 Nicolas Tessore

These lecture notes cover advanced topics in linear regression, with an in-depth exploration of the existence, uniqueness, relations, computation, and non-asymptotic properties of the most prominent estimators in this setting. The covered…

Methodology · Statistics 2025-12-05 Alberto Quaini

We study the structural and statistical properties of $\mathcal{R}$-norm minimizing interpolants of datasets labeled by specific target functions. The $\mathcal{R}$-norm is the basis of an inductive bias for two-layer neural networks,…

Machine Learning · Computer Science 2023-06-27 Navid Ardeshir , Daniel Hsu , Clayton Sanford

We present large sample results for partitioning-based least squares nonparametric regression, a popular method for approximating conditional expectation functions in statistics, econometrics, and machine learning. First, we obtain a…

Statistics Theory · Mathematics 2020-07-20 Matias D. Cattaneo , Max H. Farrell , Yingjie Feng

The paper addresses the model reduction problem for linear and nonlinear systems using the notion of least squares moment matching. For linear systems, the main idea is to approximate a transfer function by ensuring that the interpolation…

Optimization and Control · Mathematics 2021-10-13 Alberto Padoan

We consider the problem of robustly predicting as well as the best linear combination of $d$ given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. For…

Statistics Theory · Mathematics 2012-02-24 Jean-Yves Audibert , Olivier Catoni

Deep neural networks (DNNs) typically involve a large number of parameters and are trained to achieve zero or near-zero training error. Despite such interpolation, they often exhibit strong generalization performance on unseen data, a…

Machine Learning · Statistics 2026-01-23 Jingfu Peng , Yuhong Yang

Hastie et al. (2022) found that ridge regularization is essential in high dimensional linear regression $y=\beta^Tx + \epsilon$ with isotropic co-variates $x\in \mathbb{R}^d$ and $n$ samples at fixed $d/n$. However, Hastie et al. (2022)…

Statistics Theory · Mathematics 2026-05-04 Jake Freeman

A new approach to nonlinear modelling is presented which, by incorporating the global behaviour of the model, lifts shortcomings of both least squares and total least squares parameter estimates. Although ubiquitous in practice, a least…

chao-dyn · Physics 2009-10-31 Patrick E. McSharry , Leonard A. Smith