对数神经受控微分方程:李括号带来的差异
Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference
AI总结:
本文提出Log-NCDEs,利用Log-ODE方法近似CDE解,高效训练神经受控微分方程,在多达5万观测的多变量时间序列上超越现有模型。
摘要:
受控微分方程(CDE)的向量场描述了控制路径与解路径演化之间的关系。神经CDE(NCDEs)将时间序列数据视为控制路径的观测值,使用神经网络参数化CDE的向量场,并将解路径作为连续演化的隐藏状态。由于其公式对不规则采样率具有鲁棒性,NCDEs是建模现实世界数据的强大方法。基于神经粗糙微分方程(NRDEs),我们引入了Log-NCDEs,一种新颖、有效且高效的NCDE训练方法。Log-NCDEs的核心组件是Log-ODE方法,这是一种来自粗糙路径研究的工具,用于近似CDE的解。实验表明,Log-NCDEs在一系列多变量时间序列数据集(最多包含50,000个观测值)上优于NCDEs、NRDEs、线性循环单元、S5和MAMBA。
英文摘要:
The vector field of a controlled differential equation (CDE) describes the relationship between a control path and the evolution of a solution path. Neural CDEs (NCDEs) treat time series data as observations from a control path, parameterise a CDE's vector field using a neural network, and use the solution path as a continuously evolving hidden state. As their formulation makes them robust to irregular sampling rates, NCDEs are a powerful approach for modelling real-world data. Building on neural rough differential equations (NRDEs), we introduce Log-NCDEs, a novel, effective, and efficient method for training NCDEs. The core component of Log-NCDEs is the Log-ODE method, a tool from the study of rough paths for approximating a CDE's solution. Log-NCDEs are shown to outperform NCDEs, NRDEs, the linear recurrent unit, S5, and MAMBA on a range of multivariate time series datasets with up to $50{,}000$ observations.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。