English
Related papers

Related papers: Asymptotics of Ridge Regression in Convolutional M…

200 papers

Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data…

When the regressors of a econometric linear model are nonorthogonal, it is well known that their estimation by ordinary least squares can present various problems that discourage the use of this model. The ridge regression is the most…

Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the…

Machine Learning · Statistics 2024-01-15 Emmanuel Caron , Stephane Chretien

Conventional statistical wisdom established a well-understood relationship between model complexity and prediction error, typically presented as a U-shaped curve reflecting a transition between under- and overfitting regimes. However,…

Machine Learning · Statistics 2023-10-31 Alicia Curth , Alan Jeffares , Mihaela van der Schaar

Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and generalization. Recently, the double descent phenomena has been…

Machine Learning · Computer Science 2021-07-28 Ilja Kuzborskij , Csaba Szepesvári , Omar Rivasplata , Amal Rannen-Triki , Razvan Pascanu

From the sampling of data to the initialisation of parameters, randomness is ubiquitous in modern Machine Learning practice. Understanding the statistical fluctuations engendered by the different sources of randomness in prediction is…

Machine Learning · Statistics 2022-10-03 Bruno Loureiro , Cédric Gerbelot , Maria Refinetti , Gabriele Sicuro , Florent Krzakala

We obtain upper bounds for the estimation error of Kernel Ridge Regression (KRR) for all non-negative regularization parameters, offering a geometric perspective on various phenomena in KRR. As applications: 1. We address the multiple…

Statistics Theory · Mathematics 2024-10-10 Georgios Gavrilopoulos , Guillaume Lecué , Zong Shang

Methods for learning from data depend on various types of tuning parameters, such as penalization strength or step size. Since performance can depend strongly on these parameters, it is important to compare classes of estimators-by…

Statistics Theory · Mathematics 2022-06-14 Dominic Richards , Edgar Dobriban , Patrick Rebeschini

Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has limited its broader…

Statistics Theory · Mathematics 2025-11-19 Qiyang Han , Xiaocong Xu

We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden…

Statistics Theory · Mathematics 2022-03-28 Federica Gerace , Bruno Loureiro , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents under the course of learning. Understanding the mechanisms…

Machine Learning · Statistics 2024-09-20 Amanda Olmin , Fredrik Lindsten

We analyze the prediction error of ridge regression in an asymptotic regime where the sample size and dimension go to infinity at a proportional rate. In particular, we consider the role played by the structure of the true regression…

Statistics Theory · Mathematics 2021-03-09 Dominic Richards , Jaouad Mourtada , Lorenzo Rosasco

We consider fully row/column-correlated linear regression models and study several classical estimators (including minimum norm interpolators (GLS), ordinary least squares (LS), and ridge regressors). We show that \emph{Random Duality…

Machine Learning · Statistics 2024-06-14 Mihailo Stojnic

Double descent is a phenomenon of over-parameterized statistical models such as deep neural networks which have a re-descending property in their risk function. As the complexity of the model increases, risk exhibits a U-shaped region due…

Machine Learning · Statistics 2025-10-16 Nick Polson , Vadim Sokolov

Kernel methods for deconvolution have attractive features, and prevail in the literature. However, they have disadvantages, which include the fact that they are usually suitable only for cases where the error distribution is infinitely…

Statistics Theory · Mathematics 2009-09-29 Peter Hall , Alexander Meister

Estimation and prediction problems for dense signals are often framed in terms of minimax problems over highly symmetric parameter spaces. In this paper, we study minimax problems over l2-balls for high-dimensional linear models with…

Statistics Theory · Mathematics 2012-03-22 Lee Dicker

From benign overfitting in overparameterized models to rich power-law scalings in performance, simple ridge regression displays surprising behaviors sometimes thought to be limited to deep neural networks. This balance of phenomenological…

Machine Learning · Statistics 2026-05-08 Alexander Atanasov , Jacob A. Zavatone-Veth , Cengiz Pehlevan

Overparametrized models can exhibit an excellent generalization performance, although they should be prone to overfitting according to classical statistical theory. The discovery of the "double descent", indicating that the generalization…

Machine Learning · Computer Science 2026-05-22 Tino Werner

There has been growing interest in generalization performance of large multilayer neural networks that can be trained to achieve zero training error, while generalizing well on test data. This regime is known as 'second descent' and it…

Machine Learning · Statistics 2022-09-30 Eng Hock Lee , Vladimir Cherkassky

Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance trade-off, their test error often follows a "double descent" -…

Machine Learning · Computer Science 2020-04-06 Stéphane d'Ascoli , Maria Refinetti , Giulio Biroli , Florent Krzakala