4 papers
Learning switched non-linear dynamical systems from a single trajectory
Sunny G. W. Wang, Hemant Tyagi
We study empirical risk minimization for learning non-linear dynamical systems whose transition dynamics may switch over time. Under stability assumptions, and i.i.d switching over…
Joint learning of a network of linear dynamical systems via total variation penalization
Claire Donnat, Olga Klopp, Hemant Tyagi
We consider the problem of joint estimation of the parameters of linear dynamical systems, given access to single realizations of their respective trajectories, each of length…
Joint estimation of smooth graph signals from partial linear measurements
Hemant Tyagi
Given an undirected and connected graph on vertices, suppose each vertex has a latent signal associated to it. Given partial linear measurements…
Joint Learning of Linear Dynamical Systems under Smoothness Constraints
Hemant Tyagi
We consider the problem of joint learning of multiple linear dynamical systems. This has received significant attention recently under different types of assumptions on the model p…