paper-with-me

Papers

Benign Overfitting in Linear Regression

2019-06-26 · Peter L. Bartlett, Philip M. Long, Gábor Lugosi, Alexander Tsigler

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Motivated by this phenomenon, we consider when a perfect fit to training data in linear regression is compatible with accurate prediction. We give a characterization of linear regression problems for which the minimum norm interpolating prediction rule has near-optimal prediction accuracy. The characterization is in terms of two notions of the effective rank of the data covariance. It shows that overparameterization is essential for benign overfitting in this setting: the number of directions in parameter space that are unimportant for prediction must significantly exceed the sample size. By studying examples of data covariance properties that this characterization shows are required for benign overfitting, we find an important role for finite-dimensional data: the accuracy of the minimum norm interpolating prediction rule approaches the best possible accuracy for a much narrower range of properties of the data distribution when the data lies in an infinite dimensional space versus when the data lies in a finite dimensional space whose dimension grows faster than the sample size.

📄 PDF Abstract BibTeX arXiv:1906.11300

Code (0)

등록된 구현이 없습니다.

Tasks

Predictionregression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

The Implicit Bias of Benign Overfitting

2022-01-27 · Ohad Shamir

The phenomenon of benign overfitting, where a predictor perfectly fits noisy training data while attaining near-optimal expected loss, has received much attention in recent years, but still remains not fully understood b…

regression

Benign Overfitting in Adversarially Robust Linear Classification

2021-12-31 · Jinghui Chen, Yuan Cao, Quanquan Gu

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon…

Classification

Benign Overfitting in Out-of-Distribution Generalization of Linear Models

2024-12-19 · Shange Tang, Jiayun Wu, Jianqing Fan, Chi Jin

Benign overfitting refers to the phenomenon where an over-parameterized model fits the training data perfectly, including noise in the data, but still generalizes well to the unseen test data. While prior work provides s…

Out-of-Distribution Generalizationregression

Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting

2025-10-01 · Jiping Li, Rishi Sonthalia arxiv

This paper analyzes the generalization error of minimum-norm interpolating solutions in linear regression using spiked covariance data models. The paper characterizes how varying spike strengths and target-spike alignmen…

Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression

2022-02-10 · Masahiro Kato, Masaaki Imaizumi

We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models. As the development of machine learning for causal inference, a wide range of lar…

Causal Inferenceregression