paper-with-me

홈 › Papers

Benign Overfitting for Regression with Trained Two-Layer ReLU Networks

2024-10-08 · Junhyung Park, Patrick Bloebaum, Shiva Prasad Kasiviswanathan

We study the least-square regression problem with a two-layer fully-connected neural network, with ReLU activation function, trained by gradient flow. Our first result is a generalization result, that requires no assumptions on the underlying regression function or the noise other than that they are bounded. We operate in the neural tangent kernel regime, and our generalization result is developed via a decomposition of the excess risk into estimation and approximation errors, viewing gradient flow as an implicit regularizer. This decomposition in the context of neural networks is a novel perspective of gradient descent, and helps us avoid uniform convergence traps. In this work, we also establish that under the same setting, the trained network overfits to the data. Together, these results, establishes the first result on benign overfitting for finite-width ReLU networks for arbitrary regression functions.

📄 PDF Abstract BibTeX arXiv:2410.06191

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Benign Overfitting for Two-layer ReLU Convolutional Neural Networks

2023-03-07 · Yiwen Kou, Zixiang Chen, Yuanzhou Chen, Quanquan Gu

Modern deep learning models with great expressive power can be trained to overfit the training data but still generalize well. This phenomenon is referred to as \textit{benign overfitting}. Recently, a few studies have a…

Vocal Bursts Valence Prediction

Benign overfitting in leaky ReLU networks with moderate input dimension

2024-03-11 · Kedar Karhadkar, Erin George, Michael Murray, Guido Montúfar 외

The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hing…

AttributeBinary Classification

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization

2023-03-02 · Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro

Linear classifiers and leaky ReLU networks trained by gradient flow on the logistic loss have an implicit bias towards solutions which satisfy the Karush--Kuhn--Tucker (KKT) conditions for margin maximization. In this wo…

A Classical View on Benign Overfitting: The Role of Sample Size

2025-05-16 · Junhyung Park, Patrick Bloebaum, Shiva Prasad Kasiviswanathan

Benign overfitting is a phenomenon in machine learning where a model perfectly fits (interpolates) the training data, including noisy examples, yet still generalizes well to unseen data. Understanding this phenomenon has…

regression

Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks

2025-05-22 · Ichiro Hashimoto

In this paper, we prove directional convergence of network parameters of fixed width leaky ReLU two-layer neural networks optimized by gradient descent with exponential loss, which was previously only known for gradient …