中文
相关论文

相关论文: SGD Finds then Tunes Features in Two-Layer Neural …

200 篇论文

We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\boldsymbol{x}\in \mathbb{R}^d$ is Gaussian and the target $y \in \mathbb{R}$ follows a…

In recent years, stochastic gradient descent (SGD) based techniques has become the standard tools for training neural networks. However, formal theoretical understanding of why SGD can train neural networks in practice is largely missing.…

机器学习 · 计算机科学 2017-11-03 Yuanzhi Li , Yang Yuan

The mini-batch stochastic gradient descent (SGD) algorithm is widely used in training machine learning models, in particular deep learning models. We study SGD dynamics under linear regression and two-layer linear networks, with an easy…

最优化与控制 · 数学 2020-04-29 Xin Qian , Diego Klabjan

Neural networks have many successful applications, while much less theoretical understanding has been gained. Towards bridging this gap, we study the problem of learning a two-layer overparameterized ReLU neural network for multi-class…

机器学习 · 计算机科学 2019-08-02 Yuanzhi Li , Yingyu Liang

Understanding the properties of neural networks trained via stochastic gradient descent (SGD) is at the heart of the theory of deep learning. In this work, we take a mean-field view, and consider a two-layer ReLU network trained via SGD for…

机器学习 · 计算机科学 2022-05-02 Alexander Shevchenko , Vyacheslav Kungurtsev , Marco Mondelli

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

机器学习 · 统计学 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

机器学习 · 计算机科学 2026-02-26 Jianneng Yu , Alexandre V. Morozov

Neural networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learning rate schedules, momentum, and batching. These are…

神经与进化计算 · 计算机科学 2015-08-13 Thomas M. Breuel

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this…

机器学习 · 计算机科学 2025-06-13 Liu Ziyin , Hongchao Li , Masahito Ueda

How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory…

机器学习 · 计算机科学 2019-05-28 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

机器学习 · 计算机科学 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

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)…

机器学习 · 统计学 2024-07-11 Dinghao Cao , Zheng-Chu Guo , Lei Shi

Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence…

机器学习 · 计算机科学 2023-07-14 Lianke Qin , Zhao Song , Yuanyuan Yang

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

机器学习 · 统计学 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

Stochastic gradient descent (SGD) is a widely used algorithm in machine learning, particularly for neural network training. Recent studies on SGD for canonical quadratic optimization or linear regression show it attains well generalization…

机器学习 · 计算机科学 2024-09-17 Haihan Zhang , Yuanshi Liu , Qianwen Chen , Cong Fang

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

机器学习 · 计算机科学 2020-02-28 Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

Stochastic Gradient Descent (SGD) is the most popular algorithm for training deep neural networks (DNNs). As larger networks and datasets cause longer training times, training on distributed systems is common and distributed SGD variants,…

机器学习 · 计算机科学 2019-06-17 Kwangmin Yu , Thomas Flynn , Shinjae Yoo , Nicholas D'Imperio

With the rise of big data analytics, multi-layer neural networks have surfaced as one of the most powerful machine learning methods. However, their theoretical mathematical properties are still not fully understood. Training a neural…

机器学习 · 计算机科学 2021-01-01 Victor Luo , Yazhen Wang , Glenn Fung

This study explores the sample complexity for two-layer neural networks to learn a generalized linear target function under Stochastic Gradient Descent (SGD), focusing on the challenging regime where many flat directions are present at…

机器学习 · 统计学 2024-03-04 Luca Arnaboldi , Florent Krzakala , Bruno Loureiro , Ludovic Stephan

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

机器学习 · 计算机科学 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade
‹ 上一页 1 2 3 10 下一页 ›