English
Related papers

Related papers: On regularization of gradient descent, layer imbal…

200 papers

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

Machine Learning · Statistics 2025-03-19 Logan Engstrom , Andrew Ilyas , Benjamin Chen , Axel Feldmann , William Moses , Aleksander Madry

How to extract more and useful information for single image super resolution is an imperative and difficult problem. Learning-based method is a representative method for such task. However, the results are not so stable as there may exist…

Image and Video Processing · Electrical Eng. & Systems 2020-03-25 Hu Liang , Shengrong Zhao

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

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…

Machine Learning · Computer Science 2020-02-19 R. Fioresi , P. Chaudhari , S. Soatto

Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural…

Machine Learning · Computer Science 2019-06-18 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible…

Machine Learning · Computer Science 2022-11-15 Colin Ponce , Ruipeng Li , Christina Mao , Panayot Vassilevski

Deep unfolding networks have recently gained popularity in the context of solving imaging inverse problems. However, the computational and memory complexity of data-consistency layers within traditional deep unfolding networks scales with…

Image and Video Processing · Electrical Eng. & Systems 2021-06-04 Jiaming Liu , Yu Sun , Weijie Gan , Xiaojian Xu , Brendt Wohlberg , Ulugbek S. Kamilov

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

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…

Machine Learning · Computer Science 2023-01-30 Jikai Jin , Zhiyuan Li , Kaifeng Lyu , Simon S. Du , Jason D. Lee

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this problem. Some of these methods achieved considerable performance…

Machine Learning · Computer Science 2021-07-14 Zhongzhan Huang , Mingfu Liang , Senwei Liang , Wei He

Regularization is a core component of modern inverse problems, as it helps establish the well-posedness of the solution of interest. Popular regularization approaches include variational regularization and iterative regularization. The…

Optimization and Control · Mathematics 2025-08-08 Jie Gao , Cesare Molinari , Silvia Villa , Jingwei Liang

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…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

We study the type of solutions to which stochastic gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. Our results are based on a dynamical stability analysis. In the…

Machine Learning · Computer Science 2023-07-03 Mor Shpigel Nacson , Rotem Mulayoff , Greg Ongie , Tomer Michaeli , Daniel Soudry

We rigorously study the relation between the training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices. We prove that in two canonical classification tasks for multi-class…

Machine Learning · Computer Science 2025-05-19 Gerard Ben Arous , Reza Gheissari , Jiaoyang Huang , Aukosh Jagannath

Weight decay is one of the standard tricks in the neural network toolbox, but the reasons for its regularization effect are poorly understood, and recent results have cast doubt on the traditional interpretation in terms of $L_2$…

Machine Learning · Computer Science 2018-10-30 Guodong Zhang , Chaoqi Wang , Bowen Xu , Roger Grosse

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant

Recent research shows that when Gradient Descent (GD) is applied to neural networks, the loss almost never decreases monotonically. Instead, the loss oscillates as gradient descent converges to its ''Edge of Stability'' (EoS). Here, we find…

Machine Learning · Computer Science 2023-05-23 Itai Kreisler , Mor Shpigel Nacson , Daniel Soudry , Yair Carmon