English
Related papers

Related papers: Implicit regularization of deep residual networks …

200 papers

In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neural ODE and that the…

Machine Learning · Statistics 2020-01-22 Benny Avelin , Kaj Nyström

The inverse problem of supervised reconstruction of depth-variable (time-dependent) parameters in a neural ordinary differential equation (NODE) is considered, that means finding the weights of a residual network with time continuous…

Machine Learning · Computer Science 2022-02-14 George Baravdish , Gabriel Eilertsen , Rym Jaroudi , B. Tomas Johansson , Lukáš Malý , Jonas Unger

Model reduction for fluid flow simulation continues to be of great interest across a number of scientific and engineering fields. Here, we explore the use of Neural Ordinary Differential Equations, a recently introduced family of…

Machine Learning · Computer Science 2021-04-30 Sourav Dutta , Peter Rivera-Casillas , Matthew W. Farthing

Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are…

Machine Learning · Computer Science 2019-06-07 Xuanqing Liu , Tesi Xiao , Si Si , Qin Cao , Sanjiv Kumar , Cho-Jui Hsieh

The success of deep learning is due, to a large extent, to the remarkable effectiveness of gradient-based optimization methods applied to large neural networks. The purpose of this work is to propose a modern view and a general mathematical…

Machine Learning · Computer Science 2021-05-28 Chaoyue Liu , Libin Zhu , Mikhail Belkin

In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks. We show how both discrete and continuous residual layers allow for more robust training, being that continuous residual layers are…

Machine Learning · Computer Science 2019-11-27 Pedro H. C. Avelar , Anderson R. Tavares , Marco Gori , Luis C. Lamb

While the Implicit Bias(or Implicit Regularization) of standard loss functions has been studied, the optimization geometry induced by discriminative metric-learning objectives remains largely unexplored.To the best of our knowledge, this…

Machine Learning · Computer Science 2026-04-13 Jiawen Li

Neural differential equations are a promising new member in the neural network family. They show the potential of differential equations for time series data analysis. In this paper, the strength of the ordinary differential equation (ODE)…

Machine Learning · Computer Science 2020-05-21 Mansura Habiba , Barak A. Pearlmutter

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

A residual network (or ResNet) is a standard deep neural net architecture, with state-of-the-art performance across numerous applications. The main premise of ResNets is that they allow the training of each layer to focus on fitting just…

Machine Learning · Computer Science 2018-09-28 Ohad Shamir

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…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

We address the behavior of idealized deep residual neural networks (ResNets), modeled via an optimal control problem set over continuity (or adjoint transport) equations. The continuity equations describe the statistical evolution of the…

Optimization and Control · Mathematics 2025-07-14 Samuel Daudin , François Delarue

In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-time. The proposed architecture stems from the combination of Neural Ordinary Differential Equations (Neural ODEs) with the model structure of…

Systems and Control · Electrical Eng. & Systems 2023-09-18 Daniele Martinelli , Clara Lucía Galimberti , Ian R. Manchester , Luca Furieri , Giancarlo Ferrari-Trecate

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network…

Machine Learning · Computer Science 2020-10-27 Ziwei Ji , Matus Telgarsky

We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential equations driven by…

Machine Learning · Statistics 2021-12-02 Soon Hoe Lim , N. Benjamin Erichson , Liam Hodgkinson , Michael W. Mahoney

Neural networks have the ability to serve as universal function approximators, but they are not interpretable and don't generalize well outside of their training region. Both of these issues are problematic when trying to apply standard…

Machine Learning · Computer Science 2023-08-21 Colby Fronk , Linda Petzold

We investigate the asymptotic properties of deep Residual networks (ResNets) as the number of layers increases. We first show the existence of scaling regimes for trained weights markedly different from those implicitly assumed in the…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , Renyuan Xu

Determining the optimal depth of a neural network is a fundamental yet challenging problem, typically resolved through resource-intensive experimentation. This paper introduces a formal theoretical framework to address this question by…

Machine Learning · Computer Science 2025-06-23 Qian Qi

In this paper we consider Deep Neural Networks (DNNs) with a smooth activation function as surrogates for high-dimensional functions that are somewhat smooth but costly to evaluate. We consider the standard (non-periodic) DNNs as well as…

Numerical Analysis · Mathematics 2026-03-04 Alexander Keller , Frances Y. Kuo , Dirk Nuyens , Ian H. Sloan

The deep linear network (DLN) is a model for implicit regularization in gradient based optimization of overparametrized learning architectures. Training the DLN corresponds to a Riemannian gradient flow, where the Riemannian metric is…

Dynamical Systems · Mathematics 2023-05-12 Nadav Cohen , Govind Menon , Zsolt Veraszto