Spectral filtering for general linear dynamical systems

Elad Hazan; Holden Lee; Karan Singh; Cyril Zhang; Yi Zhang

Spectral filtering for general linear dynamical systems

Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English (US)
Pages (from-to)	4634-4643
Number of pages	10
Journal	Advances in Neural Information Processing Systems
Volume	2018-December
State	Published - 2018
Event	32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada Duration: Dec 2 2018 → Dec 8 2018

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{ef5324cf58d146bc8b73664aabad9176,

title = "Spectral filtering for general linear dynamical systems",

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.",

author = "Elad Hazan and Holden Lee and Karan Singh and Cyril Zhang and Yi Zhang",

note = "Publisher Copyright: {\textcopyright} 2018 Curran Associates Inc..All rights reserved.; 32nd Conference on Neural Information Processing Systems, NeurIPS 2018 ; Conference date: 02-12-2018 Through 08-12-2018",

year = "2018",

language = "English (US)",

volume = "2018-December",

pages = "4634--4643",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

}

TY - JOUR

T1 - Spectral filtering for general linear dynamical systems

AU - Hazan, Elad

AU - Lee, Holden

AU - Singh, Karan

AU - Zhang, Cyril

AU - Zhang, Yi

PY - 2018

Y1 - 2018

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85064816372&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064816372&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85064816372

SN - 1049-5258

VL - 2018-December

SP - 4634

EP - 4643

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 32nd Conference on Neural Information Processing Systems, NeurIPS 2018

Y2 - 2 December 2018 through 8 December 2018

ER -

Spectral filtering for general linear dynamical systems

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this