Searcharxiv⌕ Search

arXiv subjects

Peiying Wu

Publications and source records attributed to Peiying Wu.

3 recordsLinked to original sources

Error Analysis of Deep Learning

This review examines deep learning theory through the lens of error decomposition, systematically addressing approximation, statistical, and optimization errors. We trace the development of error analyses from bounds on individual error components to frameworks that account for all three. Using nonparametric regression and the Deep Ritz Method as dual running examples, we demonstrate how these analyses apply across fundamentally different loss structures. We then review representative analyses in scientific machine learning, generative learning, reinforcement learning, representation learning, and large language models, showing how learning errors affect solutions, distributions, and predictions through problem-specific arguments. Throughout, we clarify which error components are controlled, how they are combined, and what assumptions are needed to obtain guarantees for trained networks.

math.NA↗

DRM Revisited: A Complete Error Analysis

In this work, we address a foundational question in the theoretical analysis of the Deep Ritz Method (DRM) under the over-parameteriztion regime: Given a target precision level, how can one determine the appropriate number of training samples, the key architectural parameters of the neural networks, the step size for the projected gradient descent optimization procedure, and the requisite number of iterations, such that the output of the gradient descent process closely approximates the true solution of the underlying partial differential equation to the specified precision?

math.NA↗

Solving the inverse source problem of the fractional Poisson equation by MC-fPINNs

In this paper, we effectively solve the inverse source problem of the fractional Poisson equation using MC-fPINNs. We construct two neural networks $ u_{NN}(x;θ)$ and $f_{NN}(x;ψ)$ to approximate the solution $u^{*}(x)$ and the forcing term $f^{*}(x)$ of the fractional Poisson equation. To optimize these two neural networks, we use the Monte Carlo sampling method mentioned in MC-fPINNs and define a new loss function combining measurement data and the underlying physical model. Meanwhile, we present a comprehensive error analysis for this method, along with a prior rule to select the appropriate parameters of neural networks. Several numerical examples are given to demonstrate the great precision and robustness of this method in solving high-dimensional problems up to 10D, with various fractional order $α$ and different noise levels of the measurement data ranging from 1$\%$ to 10$\%$.

math.NA↗