paper-with-me

홈 › Papers

On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime

2021-10-06 · Zhiyan Ding, Shi Chen, Qin Li, Stephen Wright

Finding the optimal configuration of parameters in ResNet is a nonconvex minimization problem, but first-order methods nevertheless find the global optimum in the overparameterized regime. We study this phenomenon with mean-field analysis, by translating the training process of ResNet to a gradient-flow partial differential equation (PDE) and examining the convergence properties of this limiting process. The activation function is assumed to be $2$-homogeneous or partially $1$-homogeneous; the regularized ReLU satisfies the latter condition. We show that if the ResNet is sufficiently large, with depth and width depending algebraically on the accuracy and confidence levels, first-order optimization methods can find global minimizers that fit the training data.

📄 PDF Abstract BibTeX arXiv:2110.02926

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Average Pooling 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Convergence of gradient descent for learning linear neural networks

2021-08-04 · Gabin Maxime Nguegnang, Holger Rauhut, Ulrich Terstiege

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suita…

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…

Global Convergence of Four-Layer Matrix Factorization under Random Initialization

2025-11-13 · Minrui Luo, Weihang Xu, Xiang Gao, Maryam Fazel 외 arxiv

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is …

Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks

2019-12-01 · NeurIPS 2019 12 · Guodong Zhang, James Martens, Roger B. Grosse

Natural gradient descent has proven very effective at mitigating the catastrophic effects of pathological curvature in the objective function, but little is known theoretically about its convergence properties, especiall…

On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks

2024-10-10 · Yihang Gao, Vincent Y. F. Tan

Kolmogorov--Arnold Networks (KANs), a recently proposed neural network architecture, have gained significant attention in the deep learning community, due to their potential as a viable alternative to multi-layer percept…

Kolmogorov-Arnold NetworksregressionTime Series Forecasting