Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approach
Abstract
Abstract. This paper investigates approximation capabilities of 2D deep convolutional neural networks (CNNs), with Korobov functions serving as a benchmark. We focus on 2D CNNs, comprising multichannel convolutional layers with zero-padding and rectified linear unit activations, followed by a fully connected layer. We propose a fully constructive approach for building 2D CNNs to approximate Korobov functions and provide rigorous analysis of the complexity of the constructed networks. Our results demonstrate that 2D CNNs achieve near-optimal approximation rates under the continuous weight selection model, significantly alleviating the curse of dimensionality. This work provides a solid theoretical foundation for 2D CNNs and illustrates their potential for broader applications in function approximation.
Fields of Study & Subjects
Advanced Neural Network Applications
Stochastic Gradient Optimization Techniques
Model Reduction and Neural Networks
Publication details
- Journal / source
- SIAM Journal on Applied Mathematics
- Publisher
- Society for Industrial & Applied Mathematics (SIAM)
- Volume
- 86
- Issue
- 4
- Pages
- 1698–1727
- Publication date
- 13 July 2026
- Language
- EN