paper-with-me

Papers

Generalization for Least Squares Regression With Simple Spiked Covariances

2024-10-17 · Jiping Li, Rishi Sonthalia

Random matrix theory has proven to be a valuable tool in analyzing the generalization of linear models. However, the generalization properties of even two-layer neural networks trained by gradient descent remain poorly understood. To understand the generalization performance of such networks, it is crucial to characterize the spectrum of the feature matrix at the hidden layer. Recent work has made progress in this direction by describing the spectrum after a single gradient step, revealing a spiked covariance structure. Yet, the generalization error for linear models with spiked covariances has not been previously determined. This paper addresses this gap by examining two simple models exhibiting spiked covariances. We derive their generalization error in the asymptotic proportional regime. Our analysis demonstrates that the eigenvector and eigenvalue corresponding to the spike significantly influence the generalization error.

📄 PDF Abstract BibTeX arXiv:2410.13991

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

A Risk Comparison of Ordinary Least Squares vs Ridge Regression

2011-05-04 · Paramveer S. Dhillon, Dean P. Foster, Sham M. Kakade, Lyle H. Ungar

We compare the risk of ridge regression to a simple variant of ordinary least squares, in which one simply projects the data onto a finite dimensional subspace (as specified by a Principal Component Analysis) and then pe…

regression

Kernel based regression with robust loss function via iteratively reweighted least squares

2019-03-27 · Hongwei Dong, Liming Yang

Least squares kernel based methods have been widely used in regression problems due to the simple implementation and good generalization performance. Among them, least squares support vector regression (LS-SVR) and extre…

regression

Loss minimization and parameter estimation with heavy tails

2013-07-07 · Daniel Hsu, Sivan Sabato

This work studies applications and generalizations of a simple estimation technique that provides exponential concentration under heavy-tailed distributions, assuming only bounded low-order moments. We show that the tech…

parameter estimationregression

Sparse Linear Regression via Generalized Orthogonal Least-Squares

2016-02-22 · Abolfazl Hashemi, Haris Vikalo

Sparse linear regression, which entails finding a sparse solution to an underdetermined system of linear equations, can formally be expressed as an $l_0$-constrained least-squares problem. The Orthogonal Least-Squares (O…

regression

The Benefits of Implicit Regularization from SGD in Least Squares Problems

2021-08-10 · NeurIPS 2021 12 · Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu 외

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches. In this…

regression