paper-with-me

Papers

Neural Integration of Continuous Dynamics

2019-11-23 · Margaret Trautner, Sai Ravela

Neural dynamical systems are dynamical systems that are described at least in part by neural networks. The class of continuous-time neural dynamical systems must, however, be numerically integrated for simulation and learning. Here, we present a compact neural circuit for two common numerical integrators: the explicit fixed-step Runge-Kutta method of any order and the semi-implicit/predictor-corrector Adams-Bashforth-Moulton method. Modeled as constant-sized recurrent networks embedding a continuous neural differential equation, they achieve fully neural temporal output. Using the polynomial class of dynamical systems, we demonstrate the equivalence of neural and numerical integration.

📄 PDF Abstract BibTeX arXiv:1911.10309

Code (0)

등록된 구현이 없습니다.

Tasks

Numerical Integration

Similar Papers 제목 키워드 기반

Discretization of Linear Systems using the Matrix Exponential

2025-05-18 · Steven Dahdah, James Richard Forbes

Discretizing continuous-time linear systems typically requires numerical integration. This document presents a convenient method for discretizing the dynamics, input, and process noise state-space matrices of a continuou…

Numerical Integration

CENIC: Convex Error-controlled Numerical Integration for Contact

2025-11-11 · Vince Kurtz, Alejandro Castro arxiv

State-of-the-art robotics simulators operate in discrete time. This requires users to choose a time step, which is both critical and challenging: large steps can produce non-physical artifacts, while small steps force th…

Training Generative Adversarial Networks by Solving Ordinary Differential Equations

2020-10-28 · NeurIPS 2020 12 · Chongli Qin, Yan Wu, Jost Tobias Springenberg, Andrew Brock 외

The instability of Generative Adversarial Network (GAN) training has frequently been attributed to gradient descent. Consequently, recent methods have aimed to tailor the models and training procedures to stabilise the d…

Generative Adversarial Network

Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo

2026-07-14 · Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang, Andre Wibisono arxiv

We show the Randomized Hamiltonian Monte Carlo (RHMC) algorithm has accelerated mixing time guarantees for sampling from log-concave probability distributions. RHMC proceeds by repeatedly simulating the continuous-time H…

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators

2025-12-04 · Xianglong Hou, Xinquan Huang, Paris Perdikaris arxiv

Neural operator surrogates for time-dependent partial differential equations (PDEs) conventionally employ autoregressive prediction schemes, which accumulate error over long rollouts and require uniform temporal discreti…