English
Related papers

Related papers: An Investigation into Neural Net Optimization via …

200 papers

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

This paper studies generalization capabilities of neural networks (NNs) using new and improved PyTorch library Loss Landscape Analysis (LLA). LLA facilitates visualization and analysis of loss landscapes along with the properties of NN…

Machine Learning · Computer Science 2025-02-06 Nikita Gabdullin

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that overparameterization…

Machine Learning · Computer Science 2026-05-11 Kusha Sareen , Mohammad Pedramfar , Sékou-Oumar Kaba , Mehran Shakerinava , Siamak Ravanbakhsh

We investigate the approximation efficiency of score functions by deep neural networks in diffusion-based generative modeling. While existing approximation theories utilize the smoothness of score functions, they suffer from the curse of…

Machine Learning · Computer Science 2023-09-21 Song Mei , Yuchen Wu

Artificial neural networks have gone through a recent rise in popularity, achieving state-of-the-art results in various fields, including image classification, speech recognition, and automated control. Both the performance and…

Neural and Evolutionary Computing · Computer Science 2016-11-08 Sean C. Smithson , Guang Yang , Warren J. Gross , Brett H. Meyer

Many theoretical results in deep learning can be traced to symmetry or equivariance of neural networks under parameter transformations. However, existing analyses are typically problem-specific and focus on first-order consequences such as…

Machine Learning · Computer Science 2025-12-29 Yongyi Yang , Liu Ziyin

In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Zhibin Liao , Tom Drummond , Ian Reid , Gustavo Carneiro

In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients. To address the vanishing gradient issue, we study a framework, where we insert an intermediate output…

Computer Vision and Pattern Recognition · Computer Science 2019-05-31 Yi Zhou , Yue Bai , Shuvra S. Bhattacharyya , Heikki Huttunen

Recent findings by Cohen et al., 2021, demonstrate that when training neural networks using full-batch gradient descent with a step size of $\eta$, the largest eigenvalue $\lambda_{\max}$ of the full-batch Hessian consistently stabilizes…

Machine Learning · Computer Science 2025-12-30 Arseniy Andreyev , Pierfrancesco Beneventano

The integration of optimization problems within neural network architectures represents a fundamental shift from traditional approaches to handling constraints in deep learning. While it is long known that neural networks can incorporate…

Machine Learning · Computer Science 2024-12-31 Calder Katyal

This paper introduces a novel method for eigenvalue computation using a distributed cooperative neural network framework. Unlike traditional techniques that face scalability challenges in large systems, our decentralized algorithm enables…

Machine Learning · Computer Science 2024-09-20 Ronald Katende

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Romain Couillet

We propose a fresh take on understanding the mechanisms of neural networks by analyzing the rich directional structure of optimization trajectories, represented by their pointwise parameters. Towards this end, we introduce some natural…

Machine Learning · Computer Science 2024-06-25 Sidak Pal Singh , Bobby He , Thomas Hofmann , Bernhard Schölkopf

The remarkable success of Deep Neural Networks(DNN) is driven by gradient-based optimization, yet this process is often undermined by its tendency to produce disordered weight structures, which harms feature clarity and degrades learning…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Anzhe Cheng , Chenzhong Yin , Mingxi Cheng , Shukai Duan , Shahin Nazarian , Paul Bogdan

Recently, it has been observed that when training a deep neural net with SGD, the majority of the loss landscape's curvature quickly concentrates in a tiny *top* eigenspace of the loss Hessian, which remains largely stable thereafter.…

Machine Learning · Computer Science 2025-04-22 Andres Fernandez , Frank Schneider , Maren Mahsereci , Philipp Hennig

The eigendecomposition of the coupling matrix of large biological networks is central to the study of the dynamics of these networks. For neural networks, this matrix should reflect the topology of the network and conform with Dale's law…

Neurons and Cognition · Quantitative Biology 2015-09-08 Hervé Rouault , Shaul Druckmann

Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Huan Wang , Can Qin , Yulun Zhang , Yun Fu

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the…

Machine Learning · Computer Science 2025-10-29 Diego Doimo

We develop a minimax rate analysis to describe the reason that deep neural networks (DNNs) perform better than other standard methods. For nonparametric regression problems, it is well known that many standard methods attain the minimax…

Machine Learning · Statistics 2022-02-09 Masaaki Imaizumi , Kenji Fukumizu