中文
相关论文

相关论文: The Dynamics of Gradient Descent for Overparametri…

200 篇论文

This paper considers the Pointer Value Retrieval (PVR) benchmark introduced in [ZRKB21], where a 'reasoning' function acts on a string of digits to produce the label. More generally, the paper considers the learning of logical functions…

机器学习 · 计算机科学 2022-10-21 Emmanuel Abbe , Samy Bengio , Elisabetta Cornacchia , Jon Kleinberg , Aryo Lotfi , Maithra Raghu , Chiyuan Zhang

Gradient descent (GD) is a collection of continuous optimization methods that have achieved immeasurable success in practice. Owing to data science applications, GD with diminishing step sizes has become a prominent variant. While this…

最优化与控制 · 数学 2023-06-27 Vivak Patel , Albert S. Berahas

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

机器学习 · 计算机科学 2021-01-08 Kaustubh Yadav

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

机器学习 · 计算机科学 2020-02-26 Satrajit Chatterjee

Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where…

机器学习 · 计算机科学 2023-07-27 Lei Chen , Joan Bruna

Stochastic gradient descent (SGD) is a popular algorithm for optimization problems arising in high-dimensional inference tasks. Here one produces an estimator of an unknown parameter from independent samples of data by iteratively…

机器学习 · 统计学 2023-06-23 Gerard Ben Arous , Reza Gheissari , Aukosh Jagannath

Although graph neural networks (GNNs) have made great progress recently on learning from graph-structured data in practice, their theoretical guarantee on generalizability remains elusive in the literature. In this paper, we provide a…

机器学习 · 计算机科学 2020-06-26 Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

We study a continuous-time approximation of the stochastic gradient descent process for minimizing the population expected loss in learning problems. The main results establish general sufficient conditions for the convergence, extending…

机器学习 · 计算机科学 2025-11-03 Gabor Lugosi , Eulalia Nualart

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

机器学习 · 计算机科学 2017-11-23 Haiping Huang , Taro Toyoizumi

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functions. Despite its…

机器学习 · 计算机科学 2025-12-01 Yiran Zhang , Weihang Xu , Mo Zhou , Maryam Fazel , Simon Shaolei Du

It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal…

机器学习 · 计算机科学 2023-01-30 Jikai Jin , Zhiyuan Li , Kaifeng Lyu , Simon S. Du , Jason D. Lee

This paper establishes risk convergence and asymptotic weight matrix alignment --- a form of implicit regularization --- of gradient flow and gradient descent when applied to deep linear networks on linearly separable data. In more detail,…

机器学习 · 计算机科学 2019-02-26 Ziwei Ji , Matus Telgarsky

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

量子物理 · 物理学 2024-08-14 Kaiming Bian , Shitao Zhang , Fei Meng , Wen Zhang , Oscar Dahlsten

In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index regression model, in the `finite-width proportional regime'…

机器学习 · 计算机科学 2025-05-09 Qiyang Han , Masaaki Imaizumi

A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of the model exceeds a certain threshold. A large body of work in…

In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in many distributed DNN training scenarios, including the recently popular federated…

机器学习 · 计算机科学 2021-11-16 Zhong-Jing Chen , Eduin E. Hernandez , Yu-Chih Huang , Stefano Rini

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

机器学习 · 计算机科学 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

In this paper, we present some theoretical work to explain why simple gradient descent methods are so successful in solving non-convex optimization problems in learning large-scale neural networks (NN). After introducing a mathematical tool…

机器学习 · 计算机科学 2023-05-01 Hui Jiang

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

机器学习 · 计算机科学 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

In deep learning, a central issue is to understand how neural networks efficiently learn high-dimensional features. To this end, we explore the gradient descent learning of a general Gaussian Multi-index model…

机器学习 · 统计学 2026-02-06 Bohan Zhang , Zihao Wang , Hengyu Fu , Jason D. Lee