Year: 2018
Type: preprint
Abstract: We give a polynomial-time algorithm for learning latent-state linear dynamical systems without system identification, and without assumptions on the spectral radius of the system's transition matrix. The algorithm extends the recently introduced technique of spectral filtering, previously applied only to systems with a symmetric transition matrix, using a novel convex relaxation to allow for the efficient identification of phases.
Source: arXiv (Cornell University)
Authors: Hazan, Elad, Lee, Holden, Singh, Karan, Zhang, Cyril, Zhang, Yi
Institution: Princeton University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2787080146