English
Related papers

Related papers: Experiments with Rich Regime Training for Deep Lea…

200 papers

Neural networks exhibit good generalization behavior in the over-parameterized regime, where the number of network parameters exceeds the number of observations. Nonetheless, current generalization bounds for neural networks fail to explain…

Machine Learning · Computer Science 2017-10-30 Alon Brutzkus , Amir Globerson , Eran Malach , Shai Shalev-Shwartz

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero training loss, with their parameters hardly varying. In…

Optimization and Control · Mathematics 2020-01-08 Lenaic Chizat , Edouard Oyallon , Francis Bach

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

Machine Learning · Statistics 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…

Machine Learning · Computer Science 2019-02-26 Pavel Izmailov , Dmitrii Podoprikhin , Timur Garipov , Dmitry Vetrov , Andrew Gordon Wilson

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…

Machine Learning · Computer Science 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion

Among attempts at giving a theoretical account of the success of deep neural networks, a recent line of work has identified a so-called lazy training regime in which the network can be well approximated by its linearization around…

Machine Learning · Computer Science 2024-04-19 Thomas George , Guillaume Lajoie , Aristide Baratin

Despite deep neural networks' powerful representation learning capabilities, theoretical understanding of how networks can simultaneously achieve meaningful feature learning and global convergence remains elusive. Existing approaches like…

Machine Learning · Computer Science 2025-07-23 Zixiang Chen , Greg Yang , Qingyue Zhao , Quanquan Gu

Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisation dynamics of two-layer neural networks in a…

Machine Learning · Statistics 2019-06-21 Sebastian Goldt , Madhu S. Advani , Andrew M. Saxe , Florent Krzakala , Lenka Zdeborová

Biological and artificial neural networks develop internal representations that enable them to perform complex tasks. In artificial networks, the effectiveness of these models relies on their ability to build task specific representation, a…

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…

Machine Learning · Statistics 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive…

Machine Learning · Computer Science 2024-08-07 Lixin Shen , Rui Wang , Yuesheng Xu , Mingsong Yan

Several works have aimed to explain why overparameterized neural networks generalize well when trained by Stochastic Gradient Descent (SGD). The consensus explanation that has emerged credits the randomized nature of SGD for the bias of the…

Machine Learning · Computer Science 2021-02-24 Shengchao Liu , Dimitris Papailiopoulos , Dimitris Achlioptas

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient…

Machine Learning · Computer Science 2025-10-27 Bhavya Vasudeva , Jung Whan Lee , Vatsal Sharan , Mahdi Soltanolkotabi

Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method…

Machine Learning · Computer Science 2024-07-03 Hejie Ying , Mengmeng Song , Yaohong Tang , Shungen Xiao , Zimin Xiao

The use of sparse neural networks has seen rapid growth in recent years, particularly in computer vision. Their appeal stems largely from the reduced number of parameters required to train and store, as well as in an increase in learning…

Machine Learning · Computer Science 2022-06-22 Laura Graesser , Utku Evci , Erich Elsen , Pablo Samuel Castro

Modern deep neural networks have a large number of parameters, making them very hard to train. We propose DSD, a dense-sparse-dense training flow, for regularizing deep neural networks and achieving better optimization performance. In the…

Computer Vision and Pattern Recognition · Computer Science 2017-02-23 Song Han , Jeff Pool , Sharan Narang , Huizi Mao , Enhao Gong , Shijian Tang , Erich Elsen , Peter Vajda , Manohar Paluri , John Tran , Bryan Catanzaro , William J. Dally

Setting the learning rate (LR) for a deep learning model is a critical part of successful training. Choosing LRs is often done empirically with trial and error. In this work, we explore a solvable model of optimal LR schedules for a…

Disordered Systems and Neural Networks · Physics 2026-05-11 Blake Bordelon , Francesco Mori

A recent line of work studies overparametrized neural networks in the "kernel regime," i.e. when the network behaves during training as a kernelized linear predictor, and thus training with gradient descent has the effect of finding the…

Machine Learning · Computer Science 2020-02-26 Blake Woodworth , Suriya Gunasekar , Pedro Savarese , Edward Moroshko , Itay Golan , Jason Lee , Daniel Soudry , Nathan Srebro

Our community has greatly improved the efficiency of deep learning applications, including by exploiting sparsity in inputs. Most of that work, though, is for inference, where weight sparsity is known statically, and/or for specialized…

Machine Learning · Computer Science 2020-12-04 Zhangxiaowen Gong , Houxiang Ji , Christopher Fletcher , Christopher Hughes , Josep Torrellas