Approximation and estimation capability of vision transformers for hierarchical compositional models

DOI10.1016/J.ACHA.2025.101849MaRDI QIDQ6858015zbMATH OpenFDO

Authors Zhongjie Shi, Zhiying Fang, Yuan Cao

Publication date 13 February 2026

Published in Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.ACHA.2025.101849

zbMATH Keywords

convergence ratesdeep learningrates of approximationvision transformers

Mathematics Subject Classification ID

Rate of convergence, degree of approximation (41A25) Artificial neural networks and deep learning (68T07)

Cites work

• Approximating functions with multi-features by deep convolutional neural networks
• Approximation bounds for norm constrained neural networks with applications to regression and GANs
• Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula>
• Deep vs. shallow networks: an approximation theory perspective
• Error bounds for approximations with deep ReLU networks
• Fast convergence rates of deep neural networks for classification
• High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
• scientific article; zbMATH DE number 3145345 (Why is no real title available?)
• Learning ability of interpolating deep convolutional neural networks
• Learning Theory
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• New error bounds for deep ReLU networks using sparse grids
• Nonparametric regression using deep neural networks with ReLU activation function
• On the Rate of Convergence of a Classifier Based on a Transformer Encoder
• On the rate of convergence of fully connected deep neural network regression estimates
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Sparse grids
• The Barron space and the flow-induced function spaces for neural network models
• Theory of deep convolutional neural networks. II: Spherical analysis
• Theory of deep convolutional neural networks. III: Approximating radial functions
• Theory of deep convolutional neural networks: downsampling
• Universal approximation bounds for superpositions of a sigmoidal function
• Universality of deep convolutional neural networks

This page was built for publication: Approximation and estimation capability of vision transformers for hierarchical compositional models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6858015)