中文
相关论文

相关论文: Label Noise SGD Provably Prefers Flat Global Minim…

200 篇论文

Generalization is one of the most important problems in deep learning (DL). In the overparameterized regime in neural networks, there exist many low-loss solutions that fit the training data equally well. The key question is which solution…

无序系统与神经网络 · 物理学 2023-06-21 Ning Yang , Chao Tang , Yuhai Tu

The remarkable generalization ability of neural networks is usually attributed to the implicit bias of SGD, which often yields models with lower complexity using simpler (e.g. linear) and low-rank features. Recent works have provided…

机器学习 · 计算机科学 2024-10-23 Khashayar Gatmiry , Zhiyuan Li , Sashank J. Reddi , Stefanie Jegelka

Local SGD is a communication-efficient variant of SGD for large-scale training, where multiple GPUs perform SGD independently and average the model parameters periodically. It has been recently observed that Local SGD can not only achieve…

机器学习 · 计算机科学 2023-03-10 Xinran Gu , Kaifeng Lyu , Longbo Huang , Sanjeev Arora

A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD)leads to improved generalization over the full-batch regime, with recent work crediting the implicit regularization of various…

机器学习 · 计算机科学 2022-11-30 Zachary Novack , Simran Kaur , Tanya Marwah , Saurabh Garg , Zachary C. Lipton

The noise in stochastic gradient descent (SGD), caused by minibatch sampling, is poorly understood despite its practical importance in deep learning. This work presents the first systematic study of the SGD noise and fluctuations close to a…

机器学习 · 计算机科学 2022-03-09 Liu Ziyin , Kangqiao Liu , Takashi Mori , Masahito Ueda

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the role of the label noise in the training dynamics of a…

机器学习 · 统计学 2022-06-22 Loucas Pillaud-Vivien , Julien Reygner , Nicolas Flammarion

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

机器学习 · 计算机科学 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Stochastic gradient descent (SGD) forms the core optimization method for deep neural networks. While some theoretical progress has been made, it still remains unclear why SGD leads the learning dynamics in overparameterized networks to…

机器学习 · 计算机科学 2019-10-30 Mingwei Wei , David J Schwab

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and the covariance structure of gradient noise are critical for…

机器学习 · 计算机科学 2020-06-22 Jingfeng Wu , Wenqing Hu , Haoyi Xiong , Jun Huan , Vladimir Braverman , Zhanxing Zhu

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

机器学习 · 计算机科学 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

Understanding the algorithmic bias of \emph{stochastic gradient descent} (SGD) is one of the key challenges in modern machine learning and deep learning theory. Most of the existing works, however, focus on \emph{very small or even…

机器学习 · 计算机科学 2021-03-30 Jingfeng Wu , Difan Zou , Vladimir Braverman , Quanquan Gu

It has long been argued that minibatch stochastic gradient descent can generalize better than large batch gradient descent in deep neural networks. However recent papers have questioned this claim, arguing that this effect is simply a…

机器学习 · 计算机科学 2020-06-29 Samuel L. Smith , Erich Elsen , Soham De

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and…

机器学习 · 计算机科学 2023-10-26 Mathieu Even , Scott Pesme , Suriya Gunasekar , Nicolas Flammarion

Stochastic gradient descent (SGD) is one of the most popular algorithms in modern machine learning. The noise encountered in these applications is different from that in many theoretical analyses of stochastic gradient algorithms. In this…

机器学习 · 统计学 2021-09-16 Stephan Wojtowytsch

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

机器学习 · 统计学 2018-12-04 Xiaowu Dai , Yuhua Zhu

The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the training of large neural networks. To tackle this challenge, Sharpness-Aware…

机器学习 · 计算机科学 2023-10-12 Zixiang Chen , Junkai Zhang , Yiwen Kou , Xiangning Chen , Cho-Jui Hsieh , Quanquan Gu

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

机器学习 · 计算机科学 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test loss follows a decreasing-increasing-decreasing pattern (or…

机器学习 · 计算机科学 2024-05-09 Yihao Xue , Kyle Whitecross , Baharan Mirzasoleiman

Stochastic Gradient Descent (SGD) has become a cornerstone of neural network optimization due to its computational efficiency and generalization capabilities. However, the gradient noise introduced by SGD is often assumed to be uncorrelated…

机器学习 · 计算机科学 2025-12-23 Marcel Kühn , Bernd Rosenow

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