paper-with-me

Papers

Minimum $\ell_{1}$-norm interpolators: Precise asymptotics and multiple descent

2021-10-18 · Yue Li, Yuting Wei

An evolving line of machine learning works observe empirical evidence that suggests interpolating estimators -- the ones that achieve zero training error -- may not necessarily be harmful. This paper pursues theoretical understanding for an important type of interpolators: the minimum $\ell_{1}$-norm interpolator, which is motivated by the observation that several learning algorithms favor low $\ell_1$-norm solutions in the over-parameterized regime. Concretely, we consider the noisy sparse regression model under Gaussian design, focusing on linear sparsity and high-dimensional asymptotics (so that both the number of features and the sparsity level scale proportionally with the sample size). We observe, and provide rigorous theoretical justification for, a curious multi-descent phenomenon; that is, the generalization risk of the minimum $\ell_1$-norm interpolator undergoes multiple (and possibly more than two) phases of descent and ascent as one increases the model capacity. This phenomenon stems from the special structure of the minimum $\ell_1$-norm interpolator as well as the delicate interplay between the over-parameterized ratio and the sparsity, thus unveiling a fundamental distinction in geometry from the minimum $\ell_2$-norm interpolator. Our finding is built upon an exact characterization of the risk behavior, which is governed by a system of two non-linear equations with two unknowns.

📄 PDF Abstract BibTeX arXiv:2110.09502

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting

2021-06-17 · NeurIPS 2021 12 · Frederic Koehler, Lijia Zhou, Danica J. Sutherland, Nathan Srebro

We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class…

Generalization Boundsregression

Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting

2021-05-21 · NeurIPS 2021 12 · Frederic Koehler, Lijia Zhou, Danica J. Sutherland, Nathan Srebro

We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class…

Generalization Boundsregression

Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models

2021-03-08 · Zitong Yang, Yu Bai, Song Mei

Recent work showed that there could be a large gap between the classical uniform convergence bound and the actual test error of zero-training-error predictors (interpolators) such as deep neural networks. To better under…

Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view

2024-06-13 · Mihailo Stojnic

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{…

FormTime Series

On the robustness of minimum norm interpolators and regularized empirical risk minimizers

2020-12-01 · Geoffrey Chinot, Matthias Löffler, Sara van de Geer

This article develops a general theory for minimum norm interpolating estimators and regularized empirical risk minimizers (RERM) in linear models in the presence of additive, potentially adversarial, errors. In particul…