paper-with-me

홈 › Papers

Optimization dependent generalization bound for ReLU networks based on sensitivity in the tangent bundle

2023-10-26 · Dániel Rácz, Mihály Petreczky, András Csertán, Bálint Daróczy

Recent advances in deep learning have given us some very promising results on the generalization ability of deep neural networks, however literature still lacks a comprehensive theory explaining why heavily over-parametrized models are able to generalize well while fitting the training data. In this paper we propose a PAC type bound on the generalization error of feedforward ReLU networks via estimating the Rademacher complexity of the set of networks available from an initial parameter vector via gradient descent. The key idea is to bound the sensitivity of the network's gradient to perturbation of the input data along the optimization trajectory. The obtained bound does not explicitly depend on the depth of the network. Our results are experimentally verified on the MNIST and CIFAR-10 datasets.

📄 PDF Abstract BibTeX arXiv:2310.17378

Code (1)

danielracz/tansens_public 공식 구현 jax

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Tangent Space Sensitivity and Distribution of Linear Regions in ReLU Networks

2020-06-11 · Bálint Daróczy

Recent articles indicate that deep neural networks are efficient models for various learning problems. However they are often highly sensitive to various changes that cannot be detected by an independent observer. As our…

ArticlesGeneralization BoundsSensitivity

Capacity Control of ReLU Neural Networks by Basis-path Norm

2018-09-19 · Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen 외

Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property of ReLU into account. It has been shown t…

Architecture independent generalization bounds for overparametrized deep ReLU networks

2025-04-08 · Thomas Chen, Chun-Kai Kevin Chien, Patricia Muñoz Ewald, Andrew G. Moore

We prove that overparametrized neural networks are able to generalize with a test error that is independent of the level of overparametrization, and independent of the Vapnik-Chervonenkis (VC) dimension. We prove explici…

Generalization Bounds

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

2019-01-24 · Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li 외

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random…

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification

2025-10-03 · Yuanfan Li, Yunwen Lei, Zheng-Chu Guo, Yiming Ying arxiv

Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks. A natural and fundamental question is whether GD can achieve gener…