paper-with-me

홈 › Papers

Characteristic Neural Ordinary Differential Equations

2021-11-25 · Xingzi Xu, Ali Hasan, Khalil Elkhalil, Jie Ding, Vahid Tarokh

We propose Characteristic-Neural Ordinary Differential Equations (C-NODEs), a framework for extending Neural Ordinary Differential Equations (NODEs) beyond ODEs. While NODEs model the evolution of a latent variables as the solution to an ODE, C-NODE models the evolution of the latent variables as the solution of a family of first-order quasi-linear partial differential equations (PDEs) along curves on which the PDEs reduce to ODEs, referred to as characteristic curves. This in turn allows the application of the standard frameworks for solving ODEs, namely the adjoint method. Learning optimal characteristic curves for given tasks improves the performance and computational efficiency, compared to state of the art NODE models. We prove that the C-NODE framework extends the classical NODE on classification tasks by demonstrating explicit C-NODE representable functions not expressible by NODEs. Additionally, we present C-NODE-based continuous normalizing flows, which describe the density evolution of latent variables along multiple dimensions. Empirical results demonstrate the improvements provided by the proposed method for classification and density estimation on CIFAR-10, SVHN, and MNIST datasets under a similar computational budget as the existing NODE methods. The results also provide empirical evidence that the learned curves improve the efficiency of the system through a lower number of parameters and function evaluations compared with baselines.

📄 PDF Abstract BibTeX arXiv:2111.13207

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyDensity Estimation

Methods 이 논문이 사용한 방법론

NODE Neural Oblivious Decision Ensembles (NODE) is a tabular data architecture that consists of differentiable oblivious decision trees (ODT) that are trained end-to-end by…

Similar Papers 제목 키워드 기반

Long-term Time Series Forecasting based on Decomposition and Neural Ordinary Differential Equations

2023-11-08 · Seonkyu Lim, Jaehyeon Park, Seojin Kim, Hyowon Wi 외

Long-term time series forecasting (LTSF) is a challenging task that has been investigated in various domains such as finance investment, health care, traffic, and weather forecasting. In recent years, Linear-based LTSF m…

Time SeriesTime Series ForecastingWeather Forecasting

Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems

2020-10-28 · Kookjin Lee, Eric J. Parish

This work proposes an extension of neural ordinary differential equations (NODEs) by introducing an additional set of ODE input parameters to NODEs. This extension allows NODEs to learn multiple dynamics specified by the…

Decoder

Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems

2024-09-24 · Mo Zhou, Stanley Osher, Wuchen Li

Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields…

Modelling Chemical Reaction Networks using Neural Ordinary Differential Equations

2025-02-11 · Anna C. M. Thöni, William E. Robinson, Yoram Bachrach, Wilhelm T. S. Huck 외

In chemical reaction network theory, ordinary differential equations are used to model the temporal change of chemical species concentration. As the functional form of these ordinary differential equations systems is der…

Form

Deep Neural Networks Inspired by Differential Equations

2025-10-09 · Yongshuai Liu, Lianfang Wang, Kuilin Qin, Qinghua Zhang 외 arxiv

Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challeng…