Signals 4 · free daily AI digest

GRADSOLVE: fast exact gradients for ODE ensembles on GPUs

Paper recorded by Signals 4 on 2026-09-02 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-02 on arXiv · recorded by Signals 4 on 2026-09-03

Category: cs.LG · 机器学习 · first seen 2026-09-03

Abstract

Ordinary differential equations (ODEs) underlie models in science and engineering, and many applications need derivatives of their solutions with respect to parameters. Ensembles of independent trajectories suit graphics processing units (GPUs), but current GPU software forces a trade-off: the fastest ensemble solvers cannot be differentiated in reverse mode at the speed they solve, and the solver

Read on arXiv →

#144 most recent of 215 cs.LG papers we have recorded · ↑ newer: Graph Machine: Towards Better Pretraining via Edges · ↓ older: Improved Gradient Descent Lower Bounds Beyond Nesterov
Cite this page: GRADSOLVE: fast exact gradients for ODE ensembles on GPUs: the #144 most recent of 215 cs.LG papers we have recorded (as of 2026-09-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/gradsolve-fast-exact-gradients-for-ode-ensembles-on-gpus.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions