Learning the Dynamics of Sparsely Observed Interacting Systems

Abstract

We address the problem of learning the dynamics of an unknown non-parametric system linking a target and a feature time series. The feature time series is measured on a sparse and irregular grid, while we have access to only a few points of the target time series. Once learned, we can use these dynamics to predict values of the target from the previous values of the feature time series. We frame this task as learning the solution map of a controlled differential equation (CDE). By leveraging the rich theory of signatures, we are able to cast this non-linear problem as a high-dimensional linear regression. We provide an oracle bound on the prediction error which exhibits explicit dependencies on the individual-specific sampling schemes. Our theoretical results are illustrated by simulations which show that our method outperforms existing algorithms for recovering the full time series while being computationally cheap. We conclude by demonstrating its potential on real-world epidemiological data.

arXiv commentICML 2023

References in corpus (19)

• Scikit-learn: Machine Learning in Python
• Sequence to Sequence Learning with Neural Networks
• Convolutional Sequence to Sequence Learning
• Simultaneous analysis of Lasso and Dantzig selector
• Solving high-dimensional partial differential equations using deep learning
• High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
• Hamiltonian Neural Networks
• PDE-Net: Learning PDEs from Data
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• Neural Controlled Differential Equations for Irregular Time Series
• On Neural Differential Equations
• Learning from the past, predicting the statistics for the future, learning an evolving system
• Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
• Deep Signature Transforms
• Neural Rough Differential Equations for Long Time Series
• Signature Methods in Machine Learning
• Neural Controlled Differential Equations for Online Prediction Tasks
• Framing RNN as a kernel method: A neural ODE approach
• Distribution Regression for Sequential Data