English
Related papers

Related papers: Efficient implicit solvers for models of neuronal …

200 papers

The infinite-depth paradigm pioneered by Neural ODEs has launched a renaissance in the search for novel dynamical system-inspired deep learning primitives; however, their utilization in problems of non-trivial size has often proved…

Machine Learning · Computer Science 2021-01-01 Michael Poli , Stefano Massaroli , Atsushi Yamashita , Hajime Asama , Jinkyoo Park

We present an elastic simulator for domains defined as evolving implicit functions, which is efficient, robust, and differentiable with respect to both shape and material. This simulator is motivated by applications in 3D reconstruction: it…

Graphics · Computer Science 2025-04-09 Gilles Daviet , Tianchang Shen , Nicholas Sharp , David I. W. Levin

We introduce two block coordinate descent algorithms for solving optimization problems with ordinary differential equations (ODEs) as dynamical constraints. The algorithms do not need to implement direct or adjoint sensitivity analysis…

Machine Learning · Computer Science 2022-08-30 Ion Matei , Maksym Zhenirovskyy , Johan de Kleer , John Maxwell

This paper proposes a novel inverse kinematics (IK) solver of articulated robotic systems for path planning. IK is a traditional but essential problem for robot manipulation. Recently, data-driven methods have been proposed to quickly solve…

Robotics · Computer Science 2022-09-02 Suhan Park , Mathew Schwartz , Jaeheung Park

The fully implicit method is the most commonly used approach to solve black-oil problems in reservoir simulation. The method requires repeated linearization of large nonlinear systems and produces ill-condi\-tioned linear systems. We…

Numerical Analysis · Mathematics 2020-01-07 Øystein S. Klemetsdal , Atgeirr F. Rasmussen , Olav Møyner , Knut-Andreas Lie

Galaxy formation and evolution critically depend on understanding the complex photo-chemical processes that govern the evolution and thermodynamics of the InterStellar Medium (ISM). Computationally, solving chemistry is among the most heavy…

Astrophysics of Galaxies · Physics 2024-02-21 Lorenzo Branca , Andrea Pallottini

Statistical regression models whose mean functions are represented by ordinary differential equations (ODEs) can be used to describe phenomenons dynamical in nature, which are abundant in areas such as biology, climatology and genetics. The…

Methodology · Statistics 2017-05-15 Kyoungjae Lee , Jaeyong Lee , Sarat C. Dass

A key appeal of the recently proposed Neural Ordinary Differential Equation (ODE) framework is that it seems to provide a continuous-time extension of discrete residual neural networks. As we show herein, though, trained Neural ODE models…

Machine Learning · Computer Science 2023-09-12 Katharina Ott , Prateek Katiyar , Philipp Hennig , Michael Tiemann

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…

Machine Learning · Computer Science 2019-11-26 Margaret Trautner , Sai Ravela

Stiff systems of ordinary differential equations (ODEs) arise in a wide range of scientific and engineering disciplines and are traditionally solved using implicit integration methods due to their stability and efficiency. However, these…

Numerical Analysis · Mathematics 2024-12-02 Colby Fronk , Linda Petzold

We are concerned with the efficient implementation of symplectic implicit Runge-Kutta (IRK) methods applied to systems of (non-necessarily Hamiltonian) ordinary differential equations by means of Newton-like iterations. We pay particular…

Numerical Analysis · Mathematics 2017-03-23 Mikel Antoñana , Joseba Makazaga , Ander Murua

We introduce a provably stable variant of neural ordinary differential equations (neural ODEs) whose trajectories evolve on an energy functional parametrised by a neural network. Stable neural flows provide an implicit guarantee on…

Machine Learning · Computer Science 2020-03-19 Stefano Massaroli , Michael Poli , Michelangelo Bin , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Neural network-based methods for (un)conditional density estimation have recently gained substantial attention, as various neural density estimators have outperformed classical approaches in real-data experiments. Despite these empirical…

Machine Learning · Statistics 2025-10-02 Dehao Dai , Jianqing Fan , Yihong Gu , Debarghya Mukherjee

We present a dynamically load-balanced parallel $ p $-adaptive implicit high-order flux reconstruction method for under-resolved turbulence simulation. The high-order explicit first stage, singly diagonal implicit Runge-Kutta (ESDIRK)…

Computational Physics · Physics 2020-07-15 Lai Wang , Matthias K. Gobbert , Meilin Yu

Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have…

Robotics · Computer Science 2023-03-01 Dongyu Yan , Xiaoyang Lyu , Jieqi Shi , Yi Lin

We study gradient-based optimization methods obtained by directly discretizing a second-order ordinary differential equation (ODE) related to the continuous limit of Nesterov's accelerated gradient method. When the function is smooth…

Optimization and Control · Mathematics 2018-11-29 Jingzhao Zhang , Aryan Mokhtari , Suvrit Sra , Ali Jadbabaie

This work constructs and analyzes new efficient high-order two-derivative diagonally implicit Runge--Kutta (TDDIRK) schemes with optimized phase errors. Specifically, we present a convergence result for TDDIRK methods and investigate their…

Numerical Analysis · Mathematics 2025-12-18 Julius Ehigie , Vu Thai Luan

Neural ordinary differential equations describe how values change in time. This is the reason why they gained importance in modeling sequential data, especially when the observations are made at irregular intervals. In this paper we propose…

Machine Learning · Computer Science 2021-10-26 Marin Biloš , Johanna Sommer , Syama Sundar Rangapuram , Tim Januschowski , Stephan Günnemann

The splitting method is a powerful method for solving partial differential equations. Various splitting methods have been designed to separate different physics, nonlinearities, and so on. Recently, a new splitting approach has been…

Numerical Analysis · Mathematics 2023-03-22 Yalchin Efendiev , Wing Tat Leung , Wenyuan Li , Zecheng Zhang

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration,…

Machine Learning · Computer Science 2026-05-22 Alexander Tyurin