Skip to main content

Learning Linear Dynamical Systems via Spectral Filtering

Author(s): Hazan, Elad; Singh, Karan; Zhang, Cyril

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1154m
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHazan, Elad-
dc.contributor.authorSingh, Karan-
dc.contributor.authorZhang, Cyril-
dc.date.accessioned2021-10-08T19:49:22Z-
dc.date.available2021-10-08T19:49:22Z-
dc.date.issued2017en_US
dc.identifier.citationHazan, Elad, Karan Singh, and Cyril Zhang. "Learning Linear Dynamical Systems via Spectral Filtering." In Advances in Neural Information Processing Systems 30 (2017).en_US
dc.identifier.issn1049-5258-
dc.identifier.urihttps://proceedings.neurips.cc/paper/2017/file/165a59f7cf3b5c4396ba65953d679f17-Paper.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1154m-
dc.description.abstractWe present an efficient and practical algorithm for the online prediction of discrete-time linear dynamical systems with a symmetric transition matrix. We circumvent the non-convex optimization problem using improper learning: carefully overparameterize the class of LDSs by a polylogarithmic factor, in exchange for convexity of the loss functions. From this arises a polynomial-time algorithm with a near-optimal regret guarantee, with an analogous sample complexity bound for agnostic learning. Our algorithm is based on a novel filtering technique, which may be of independent interest: we convolve the time series with the eigenvectors of a certain Hankel matrix.en_US
dc.language.isoen_USen_US
dc.relation.ispartofAdvances in Neural Information Processing Systemsen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleLearning Linear Dynamical Systems via Spectral Filteringen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
LinearDynamicalSystemsSpectral.pdf601.14 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.