paper-with-me

홈 › Papers

DISE: Dynamic Integrator Selection to Minimize Forward Pass Time in Neural ODEs

2021-01-01 · Soyoung Kang, Ganghyeon Park, Kwang-Sung Jun, Noseong Park

Neural ordinary differential equations (Neural ODEs) are appreciated for their ability to significantly reduce the number of parameters when constructing a neural network. On the other hand, they are blamed for their procrastinated forward-pass inference, which is incurred by solving integral problems. To improve the model accuracy, they rely on advanced solvers, such as the Dormand--Prince (DOPRI) method. To solve an integral problem, however, it requires at least tens (or sometimes hundreds) of steps in many Neural ODE experiments. In this work, we propose to i) directly regularize the step size of DOPRI to make the forward-pass faster and ii) dynamically choose a simpler integrator than DOPRI for a carefully selected subset of input. Because it is not the case that every input requires the advanced integrator, we design an auxiliary neural network to choose an appropriate integrator given input to decrease the overall inference time without significantly sacrificing accuracy. We consider the Euler method, the fourth-order Runge--Kutta (RK4) method, and DOPRI as selection candidates. We found that a non-trivial percentage of cases can be solved with simple integrators. Therefore, the overall number of functional evaluations (NFEs) decreases up to 78% with improved accuracy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Integrator Forwading Design for Unicycles with Constant and Actuated Velocity in Polar Coordinates

2025-09-29 · Miroslav Krstic, Velimir Todorovski, Kwang Hak Kim, Alessandro Astolfi arxiv

In a companion paper, we present a modular framework for unicycle stabilization in polar coordinates that provides smooth steering laws through backstepping. Surprisingly, the same problem also allows the application of …

An Exact Bitwise Reversible Integrator

2022-07-15 · Jos Stam

At a fundamental level most physical equations are time reversible. In this paper we propose an integrator that preserves this property at the discrete computational level. Our simulations can be run forward and backward…

Learned Lagrangian Models of PDEs via Euler-Lagrange Residual Minimization

2026-05-08 · Lyra Zhornyak, Eric Forgoston, M. Ani Hsieh arxiv

We present the first method to directly use a learned continuous Lagrangian to forecast the dynamics of systems governed by partial differential equations, exploiting the inherent conservative structure to achieve stable…

Multistep Frequency Response Optimized Integrators and Their Application to Accelerating a Power System Transient Simulation Scheme

2020-11-02 · Sheng Lei, Alexander Flueck

This paper proposes several explicit and implicit multistep frequency response optimized integrators considering first or second order derivative. A prediction-based method aiming at accelerating a novel power system tra…

Prediction

Bearing-Only Solution for Fermat-Weber Location Problem: Generalized Algorithms

2024-10-24 · Nhat-Minh Le-Phan, Phuoc Doan Nguyen, Hyo-Sung Ahn, Minh Hoang Trinh

This paper presents novel algorithms for the Fermat-Weber Location Problem, guiding an autonomous agent to the point that minimizes the weighted sum of Euclidean distances to some beacons using only bearing measurements.…