中文
相关论文

相关论文: The Limiting Dynamics of SGD: Modified Loss, Phase…

200 篇论文

Learning in deep neural networks (DNNs) is implemented through minimizing a highly non-convex loss function, typically by a stochastic gradient descent (SGD) method. This learning process can effectively find good wide minima without being…

机器学习 · 计算机科学 2021-07-27 Guozhang Chen , Cheng Kevin Qu , Pulin Gong

In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of…

机器学习 · 计算机科学 2025-05-13 Davide Barbieri , Matteo Bonforte , Peio Ibarrondo

Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not…

Understanding the dynamics of neural network parameters during training is one of the key challenges in building a theoretical foundation for deep learning. A central obstacle is that the motion of a network in high-dimensional parameter…

机器学习 · 计算机科学 2021-03-30 Daniel Kunin , Javier Sagastuy-Brena , Surya Ganguli , Daniel L. K. Yamins , Hidenori Tanaka

Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-to-saddle dynamics, the impact of stochastic gradient…

机器学习 · 计算机科学 2026-04-09 Guillaume Corlouer , Avi Semler , Alexander Strang , Alexander Gietelink Oldenziel

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

Stochastic gradient descent (SGD) is widely used in deep learning due to its computational efficiency, but a complete understanding of why SGD performs so well remains a major challenge. It has been observed empirically that most…

机器学习 · 统计学 2022-06-20 Carmina Fjellström , Kaj Nyström

Despite tremendous success of deep neural network in machine learning, the underlying reason for its superior learning capability remains unclear. Here, we present a framework based on statistical physics to study dynamics of stochastic…

机器学习 · 计算机科学 2021-01-19 Yu Feng , Yuhai Tu

Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for…

机器学习 · 统计学 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin

The algorithms used to train neural networks, like stochastic gradient descent (SGD), have close parallels to natural processes that navigate a high-dimensional parameter space -- for example protein folding or evolution. Our study uses a…

机器学习 · 计算机科学 2023-06-07 Shishir Adhikari , Alkan Kabakçıoğlu , Alexander Strang , Deniz Yuret , Michael Hinczewski

Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (ML), can be recast through a continuous-time approximation as a Fokker-Planck equation for Langevin dynamics, a viewpoint that has…

机器学习 · 统计学 2025-08-19 Hiroshi Horii , Sothea Has

Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight space, as indicated by small eigenvalues of the Hessian of…

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

机器学习 · 计算机科学 2023-05-30 Mingze Wang , Chao Ma

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

机器学习 · 计算机科学 2018-01-17 Pratik Chaudhari , Stefano Soatto

Stochastic gradient descent (SGD) is a key ingredient in the training of deep neural networks and yet its geometrical significance appears elusive. We study a deterministic model in which the trajectories of our dynamical systems are…

机器学习 · 计算机科学 2020-02-19 R. Fioresi , P. Chaudhari , S. Soatto

This paper studies the high-dimensional scaling limits of online stochastic gradient descent (SGD). Building on the recent work of Ben Arous, Gheissari, and Jagannath on the effective dynamics of SGD, we study the critical scaling regime of…

机器学习 · 统计学 2026-05-01 Parsa Rangriz

We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD algorithm weakly…

机器学习 · 统计学 2018-03-06 Wenqing Hu , Chris Junchi Li , Lei Li , Jian-Guo Liu

Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased…

机器学习 · 统计学 2019-06-11 Zhanxing Zhu , Jingfeng Wu , Bing Yu , Lei Wu , Jinwen Ma

While stochastic gradient descent (SGD) and variants have been surprisingly successful for training deep nets, several aspects of the optimization dynamics and generalization are still not well understood. In this paper, we present new…

机器学习 · 计算机科学 2019-07-26 Xinyan Li , Qilong Gu , Yingxue Zhou , Tiancong Chen , Arindam Banerjee

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural…

机器学习 · 统计学 2022-03-28 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová
‹ 上一页 1 2 3 10 下一页 ›