用隐函数雅可比矩阵实现参数高效的连续时间序列建模
Parameter-Efficient Neural CDEs via Implicit Function Jacobians
- 通过隐函数雅可比矩阵减少参数量
- 保持与连续RNN相似的时序建模能力
- 适合资源受限场景下的时序数据研究
神经控制微分方程（Neural CDEs, NCDEs）是一类专为分析时间序列设计的独特方法。然而，其主要缺点是模型参数数量庞大。本文提出一种参数高效的神经控制微分方程新思路，显著降低参数量，同时保留了与连续RNN类似的逻辑结构，使模型更高效且易于部署。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。