English
Related papers

Related papers: Sparsity in Continuous-Depth Neural Networks

200 papers

In complex physical systems, conventional differential equations often fall short in capturing non-local and memory effects, as they are limited to local dynamics and integer-order interactions. This study introduces a stepwise data-driven…

Computational Physics · Physics 2025-05-30 Xiangnan Yu , Hao Xu , Zhiping Mao , HongGuang Sun , Yong Zhang , Dongxiao Zhang , Yuntian Chen

Sparse recovery in linear systems underpins applications from signal processing to high-dimensional regression. Sparse Bayesian Learning, grounded in the principle of automatic relevance determination (ARD), offers a practical Bayesian…

Dosing models often use differential equations to model biological dynamics. Neural differential equations in particular can learn to predict the derivative of a process, which permits predictions at irregular points of time. However, this…

Machine Learning · Computer Science 2023-06-27 Stav Belogolovsky , Ido Greenberg , Danny Eytan , Shie Mannor

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compressed sensing which combines the pruning and training into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Jonathan W. Siegel , Jianhong Chen , Pengchuan Zhang , Jinchao Xu

Generalization to out-of-distribution (OOD) data is a critical challenge in machine learning. Ensemble-based methods, like weight space ensembles that interpolate model parameters, have been shown to achieve superior OOD performance.…

Machine Learning · Computer Science 2024-07-16 Yong Lin , Lu Tan , Yifan Hao , Honam Wong , Hanze Dong , Weizhong Zhang , Yujiu Yang , Tong Zhang

We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models in various gray-box settings which incorporates prior knowledge in the form of systems of ordinary differential equations. NDS uses neural networks to…

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

This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity concept in statistical learning and compressive sensing. By allowing arbitrary structures on the feature…

Methodology · Statistics 2009-05-05 Junzhou Huang , Tong Zhang , Dimitris Metaxas

This paper examines the impact of static sparsity on the robustness of a trained network to weight perturbations, data corruption, and adversarial examples. We show that, up to a certain sparsity achieved by increasing network width and…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Lukas Timpl , Rahim Entezari , Hanie Sedghi , Behnam Neyshabur , Olga Saukh

Modeling dynamical systems is crucial across the science and engineering fields for accurate prediction, control, and decision-making. Recently, machine learning (ML) approaches, particularly neural ordinary differential equations (NODEs),…

Systems and Control · Electrical Eng. & Systems 2026-04-20 Fatima Al-Janahi , Min-Seung Ko , Hao Zhu

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly…

Recently, Neural Ordinary Differential Equations has emerged as a powerful framework for modeling physical simulations without explicitly defining the ODEs governing the system, but instead learning them via machine learning. However, the…

Network (or graph) sparsification compresses a graph by removing inessential edges. By reducing the data volume, it accelerates or even facilitates many downstream analyses. Still, the accuracy of many sparsification methods, with…

Social and Information Networks · Computer Science 2023-09-28 Zhen Su , Jürgen Kurths , Henning Meyerhenke

Latent neural stochastic differential equations (SDEs) have recently emerged as a promising approach for learning generative models from stochastic time series data. However, they systematically underestimate the noise level inherent in…

Machine Learning · Computer Science 2025-06-11 Linus Heck , Maximilian Gelbrecht , Michael T. Schaub , Niklas Boers

Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability for dynamics-governed time-series, NODEs present a few…

Machine Learning · Computer Science 2021-08-18 Alexander Norcliffe , Cristian Bodnar , Ben Day , Jacob Moss , Pietro Liò

Continuous deep learning architectures enable learning of flexible probabilistic models for predictive modeling as neural ordinary differential equations (ODEs), and for generative modeling as continuous normalizing flows. In this work, we…

Machine Learning · Computer Science 2021-11-22 Lucas Liebenwein , Ramin Hasani , Alexander Amini , Daniela Rus

Sparse regression on a library of candidate features has developed as the prime method to discover the partial differential equation underlying a spatio-temporal data-set. These features consist of higher order derivatives, limiting model…

Machine Learning · Computer Science 2021-05-05 Gert-Jan Both , Gijs Vermarien , Remy Kusters

A common technique for ameliorating the computational costs of running large neural models is sparsification, or the pruning of neural connections during training. Sparse models are capable of maintaining the high accuracy of state of the…

Machine Learning · Computer Science 2024-12-16 Wyatt Mackey , Ioannis Schizas , Jared Deighton , David L. Boothe, , Vasileios Maroulas

We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these…

Machine Learning · Computer Science 2012-03-27 Emile Richard , Andreas Argyriou , Theodoros Evgeniou , Nicolas Vayatis

Deep neural networks (DNNs) are used in many applications, but their large size and high computational cost make them hard to run on devices with limited resources. Two widely used techniques to address this challenge are weight…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Dan Liu , Nikita Dvornik , Xue Liu