1 citations · 1 across the 7 of their papers we have counts for
7 papers
Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
Yanming Lai, Defeng Sun, Yang Wang
In contrast to most studies on neural network approximation theory that characterize results through a single parameter, such as the total number of network parameters, \cite{shen2…
Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective
Yuling Jiao, Yanming Lai, Yang Wang +1
The Transformer model is widely used in various application areas of machine learning, such as natural language processing. This paper investigates the approximation of the Hölder…
Approximation Bounds for Transformer Networks with Application to Regression
Yuling Jiao, Yanming Lai, Defeng Sun +2
We explore the approximation capabilities of Transformer networks for Hölder and Sobolev functions, and apply these results to address nonparametric regression estimation with depe…
Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching
Yuling Jiao, Wensen Ma, Defeng Sun +2
Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified. We formulate representation learning as Distribution Matching…
Approximation Bounds for Recurrent Neural Networks with Application to Regression
Yuling Jiao, Yang Wang, Bokai Yan
We study the approximation capacity of deep ReLU recurrent neural networks (RNNs) and explore the convergence properties of nonparametric least squares regression using RNNs. We de…
Error Analysis of Three-Layer Neural Network Trained with PGD for Deep Ritz Method
Yuling Jiao, Yanming Lai, Yang Wang
Machine learning is a rapidly advancing field with diverse applications across various domains. One prominent area of research is the utilization of deep learning techniques for so…
Convergence Analysis of Flow Matching in Latent Space with Transformers
Yuling Jiao, Yanming Lai, Yang Wang +1
We present theoretical convergence guarantees for ODE-based generative models, specifically flow matching. We use a pre-trained autoencoder network to map high-dimensional original…