paper-with-me

Papers

Stochastic Gradient Descent for Two-layer Neural Networks

2024-07-10 · Dinghao Cao, Zheng-Chu Guo, Lei Shi

This paper presents a comprehensive study on the convergence rates of the stochastic gradient descent (SGD) algorithm when applied to overparameterized two-layer neural networks. Our approach combines the Neural Tangent Kernel (NTK) approximation with convergence analysis in the Reproducing Kernel Hilbert Space (RKHS) generated by NTK, aiming to provide a deep understanding of the convergence behavior of SGD in overparameterized two-layer neural networks. Our research framework enables us to explore the intricate interplay between kernel methods and optimization processes, shedding light on the optimization dynamics and convergence properties of neural networks. In this study, we establish sharp convergence rates for the last iterate of the SGD algorithm in overparameterized two-layer neural networks. Additionally, we have made significant advancements in relaxing the constraints on the number of neurons, which have been reduced from exponential dependence to polynomial dependence on the sample size or number of iterations. This improvement allows for more flexibility in the design and scaling of neural networks, and will deepen our theoretical understanding of neural network models trained with SGD.

📄 PDF Abstract BibTeX arXiv:2407.07670

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
NTK 설명 없음

Similar Papers 제목 키워드 기반

Training a Two Layer ReLU Network Analytically

2023-04-06 · Adrian Barbu

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical po…

Vocal Bursts Valence Prediction

Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks

2022-01-28 · Bartłomiej Polaczyk, Jacek Cyranka

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functi…

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks for the Poisson Equation

2025-08-29 · Bangti Jin, Longjun Wu arxiv

Physics informed neural networks (PINNs) represent a very popular class of neural solvers for partial differential equations. In practice, one often employs stochastic gradient descent type algorithms to train the neural…

Stochastic Optimization

Neural ODEs as the Deep Limit of ResNets with constant weights

2019-06-28 · arXiv 2019 6 · Benny Avelin, Kaj Nyström

In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neu…

Noise-induced degeneration in online learning

2020-08-24 · Yuzuru Sato, Daiji Tsutsui, Akio Fujiwara

In order to elucidate the plateau phenomena caused by vanishing gradient, we herein analyse stability of stochastic gradient descent near degenerated subspaces in a multi-layer perceptron. In stochastic gradient descent …