Parameter-Efficient Neural CDEs via Implicit Function Jacobians

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kuleshov, Ilya, Zaytsev, Alexey
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918261736603648
author Kuleshov, Ilya
Zaytsev, Alexey
author_facet Kuleshov, Ilya
Zaytsev, Alexey
contents Neural Controlled Differential Equations (Neural CDEs, NCDEs) are a unique branch of methods, specifically tailored for analysing temporal sequences. However, they come with drawbacks, the main one being the number of parameters, required for the method's operation. In this paper, we propose an alternative, parameter-efficient look at Neural CDEs. It requires much fewer parameters, while also presenting a very logical analogy as the "Continuous RNN", which the Neural CDEs aspire to.
format Preprint
id arxiv_https___arxiv_org_abs_2512_20625
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Parameter-Efficient Neural CDEs via Implicit Function Jacobians
Kuleshov, Ilya
Zaytsev, Alexey
Machine Learning
Artificial Intelligence
Neural Controlled Differential Equations (Neural CDEs, NCDEs) are a unique branch of methods, specifically tailored for analysing temporal sequences. However, they come with drawbacks, the main one being the number of parameters, required for the method's operation. In this paper, we propose an alternative, parameter-efficient look at Neural CDEs. It requires much fewer parameters, while also presenting a very logical analogy as the "Continuous RNN", which the Neural CDEs aspire to.
title Parameter-Efficient Neural CDEs via Implicit Function Jacobians
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.20625