中文
相关论文

相关论文: Implicit Compressibility of Overparametrized Neura…

200 篇论文

Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks. Recent empirical studies have illustrated that even simple pruning…

机器学习 · 统计学 2021-06-08 Melih Barsbey , Milad Sefidgaran , Murat A. Erdogdu , Gaël Richard , Umut Şimşekli

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

计算与语言 · 计算机科学 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in stochastic optimization. Gradient clipping has emerged as a…

最优化与控制 · 数学 2025-07-10 Florian Hübler , Ilyas Fatkhullin , Niao He

It has repeatedly been observed that loss minimization by stochastic gradient descent (SGD) leads to heavy-tailed distributions of neural network parameters. Here, we analyze a continuous diffusion approximation of SGD, called homogenized…

机器学习 · 统计学 2024-02-05 Zhe Jiao , Martin Keller-Ressel

Recent studies have shown that heavy tails can emerge in stochastic optimization and that the heaviness of the tails have links to the generalization error. While these studies have shed light on interesting aspects of the generalization…

机器学习 · 统计学 2023-02-14 Anant Raj , Melih Barsbey , Mert Gürbüzbalaban , Lingjiong Zhu , Umut Şimşekli

In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the…

最优化与控制 · 数学 2021-06-15 Mert Gurbuzbalaban , Umut Şimşekli , Lingjiong Zhu

In this paper, we propose a new accelerated stochastic first-order method called clipped-SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in stochastic gradients and derive the first high-probability…

最优化与控制 · 数学 2020-10-26 Eduard Gorbunov , Marina Danilova , Alexander Gasnikov

In the era of large-scale neural network models, optimization algorithms often struggle with generalization due to an overreliance on training loss. One key insight widely accepted in the machine learning community is the idea that wide…

机器学习 · 计算机科学 2025-09-01 Bodu Gong , Gustavo Enrique Batista , Pierre Lafaye de Micheaux

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

机器学习 · 计算机科学 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song

The injection of heavy-tailed noise into the iterates of stochastic gradient descent (SGD) has garnered growing interest in recent years due to its theoretical and empirical benefits for optimization and generalization. However, its…

机器学习 · 统计学 2025-05-13 Umut Şimşekli , Mert Gürbüzbalaban , Sinan Yıldırım , Lingjiong Zhu

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

机器学习 · 计算机科学 2026-04-10 Zeran Johannsen

Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. While the empirical success of SGD is often attributed to its computational efficiency…

机器学习 · 统计学 2022-06-16 Courtney Paquette , Elliot Paquette , Ben Adlam , Jeffrey Pennington

There is an increasing realization that algorithmic inductive biases are central in preventing overfitting; empirically, we often see a benign overfitting phenomenon in overparameterized settings for natural learning algorithms, such as…

机器学习 · 计算机科学 2021-10-14 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Sham M. Kakade

Gaussian noise injections (GNIs) are a family of simple and widely-used regularisation methods for training neural networks, where one injects additive or multiplicative Gaussian noise to the network activations at every iteration of the…

The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to individual runs of an algorithm. While many works provide high-probability guarantees, quantifying…

机器学习 · 计算机科学 2026-02-06 Aleksandar Armacki , Dragana Bajović , Dušan Jakovetić , Soummya Kar , Ali H. Sayed

Stochastic gradient descent (SGD) and its variants enable modern artificial intelligence. However, theoretical understanding lags far behind their empirical success. It is widely believed that SGD has a curious ability to avoid sharp local…

机器学习 · 计算机科学 2025-10-27 Xingyu Wang , Chang-Han Rhee

Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how…

机器学习 · 计算机科学 2026-03-25 Shengping Xie , Zekun Wu , Quan Chen , Kaixu Tang

Recent theoretical studies have shown that heavy-tails can emerge in stochastic optimization due to `multiplicative noise', even under surprisingly simple settings, such as linear regression with Gaussian data. While these studies have…

机器学习 · 统计学 2025-05-06 Mert Gurbuzbalaban , Yuanhan Hu , Umut Simsekli , Kun Yuan , Lingjiong Zhu

Training Deep Neural Networks (DNNs) with small batches using Stochastic Gradient Descent (SGD) yields superior test performance compared to larger batches. The specific noise structure inherent to SGD is known to be responsible for this…

机器学习 · 统计学 2024-02-14 Tom Sander , Maxime Sylvestre , Alain Durmus

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 dynamics of stochastic gradient descent over diagonal linear…

机器学习 · 计算机科学 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion
‹ 上一页 1 2 3 10 下一页 ›