paper-with-me

홈 › Papers

How Neural Networks Learn the Support is an Implicit Regularization Effect of SGD

2024-06-17 · Pierfrancesco Beneventano, Andrea Pinto, Tomaso Poggio

We investigate the ability of deep neural networks to identify the support of the target function. Our findings reveal that mini-batch SGD effectively learns the support in the first layer of the network by shrinking to zero the weights associated with irrelevant components of input. In contrast, we demonstrate that while vanilla GD also approximates the target function, it requires an explicit regularization term to learn the support in the first layer. We prove that this property of mini-batch SGD is due to a second-order implicit regularization effect which is proportional to $\eta / b$ (step size / batch size). Our results are not only another proof that implicit regularization has a significant impact on training optimization dynamics but they also shed light on the structure of the features that are learned by the network. Additionally, they suggest that smaller batches enhance feature interpretability and reduce dependency on initialization.

📄 PDF Abstract BibTeX arXiv:2406.11110

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Implicit Regularization in Deep Matrix Factorization

2019-05-31 · NeurIPS 2019 12 · Sanjeev Arora, Nadav Cohen, Wei Hu, Yuping Luo

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the…

Matrix Completion

Estimating Implicit Regularization in Deep Learning

2026-05-06 · Joseph H. Rudoler, Kevin Tan, Giles Hooker, Konrad P. Kording arxiv

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit re…

Incremental Learning in Diagonal Linear Networks

2022-08-31 · Raphaël Berthier

Diagonal linear networks (DLNs) are a toy simplification of artificial neural networks; they consist in a quadratic reparametrization of linear regression inducing a sparse implicit regularization. In this paper, we desc…

Incremental Learningregression

Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization

2018-11-14 · Senwei Liang, Yuehaw Khoo, Haizhao Yang

Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activatio…

image-classificationImage Classification

The Implicit Regularization of Momentum Gradient Descent with Early Stopping

2022-01-14 · Li Wang, Yingcong Zhou, Zhiguo Fu

The study on the implicit regularization induced by gradient-based optimization is a longstanding pursuit. In the present paper, we characterize the implicit regularization of momentum gradient descent (MGD) with early s…

regression