Optimal Approximation and Generalization Errors for Deep Convolutional Neural Networks

Дата публикации: 17-08-2026 20:26:00

This paper focuses on approximation and learning performances of deep convolutional neural networks with zero-padding and max-pooling. We prove that, to approximate $r$-smooth function, the approximation rates of deep convolutional neural networks with depth $L$ are of order $ (L/\log L)^{-2r/d} $, which is optimal up to a logarithmic factor. Furthermore, we deduce almost optimal generalization errors for implementing empirical risk minimization over deep convolutional neural networks. Our theoretical results are verified by several numerical experiments to show the power of the convolutional structure, zero-padding and max-pooling.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width	0	3.84	17-08-2026
2	Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data	0	4.36	17-08-2026
3	High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks	0	8.7	17-08-2026
4	Nonlocal Techniques for the Analysis of Deep ReLU Neural Network Approximations	0	6.62	17-08-2026
5	Near-optimal Delta-convex Estimation of Lipschitz Functions	0	9.71	17-08-2026
6	Statistical Learning Theory for Neural Operators	0	10.21	17-08-2026
7	Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks	0	5	17-08-2026
8	A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization	0	9.82	17-08-2026
9	Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes	0	7.52	17-08-2026
10	The Sample Complexity of Parameter-Free Stochastic Convex Optimization	0	5.7	17-08-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 7.31. Источник: jmlr.org.