Learning Networks of Stochastic Differential Equations
Abstract
We consider linear models for stochastic dynamics. Any such model can be associated a network (namely a directed graph) describing which degrees of freedom interact under the dynamics. We tackle the problem of learning such a network from observation of the system trajectory over a time interval T. We analyse the l1-regularized least squares algorithm and, in the setting in which the underlying network is sparse, we prove performance guarantees that are uniform in the sampling rate as long as this is sufficiently high. This result substantiates the notion of a well defined ‘time complexity’ for the network inference problem.
Cite
Text
Pereira et al. "Learning Networks of Stochastic Differential Equations." Neural Information Processing Systems, 2010.Markdown
[Pereira et al. "Learning Networks of Stochastic Differential Equations." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/pereira2010neurips-learning/)BibTeX
@inproceedings{pereira2010neurips-learning,
title = {{Learning Networks of Stochastic Differential Equations}},
author = {Pereira, José and Ibrahimi, Morteza and Montanari, Andrea},
booktitle = {Neural Information Processing Systems},
year = {2010},
pages = {172-180},
url = {https://mlanthology.org/neurips/2010/pereira2010neurips-learning/}
}