Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems

We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-02
Hauptverfasser: Dong, Zhe, Seybold, Bryan A, Murphy, Kevin P, Bui, Hung H
Format: Artikel
Sprache:eng
Schlagworte:
Continuity (mathematics)
Dynamical systems
Inference
Nonlinear dynamics
Nonlinear systems
Switching
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Dong, Zhe
Seybold, Bryan A
Murphy, Kevin P
Bui, Hung H
description We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2307882338</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307882338</sourcerecordid><originalsourceid>FETCH-proquest_journals_23078823383</originalsourceid><addsrcrecordid>eNqNjrEKwjAURYMgWLT_EHAuxMTarFIVXVwqriXUV01Jk5qXIvr1ZvADnM4dDpczIQkXYpXJNeczkiJ2jDG-KXiei4RUpTNGDQg3uu2dD_oT11V5rYJ2Vhl6si14sA3Q1nlavXRoHtre6dlZoy0oT3dvq3rdRLd6Y4AeF2TaKoOQ_jgny8P-Uh6zwbvnCBjqzo0-nmPNBSukjH1S_Gd9AX2nQKY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2307882338</pqid></control><display><type>article</type><title>Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems</title><source>Free E- Journals</source><creator>Dong, Zhe ; Seybold, Bryan A ; Murphy, Kevin P ; Bui, Hung H</creator><creatorcontrib>Dong, Zhe ; Seybold, Bryan A ; Murphy, Kevin P ; Bui, Hung H</creatorcontrib><description>We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Continuity (mathematics) ; Dynamical systems ; Inference ; Nonlinear dynamics ; Nonlinear systems ; Switching</subject><ispartof>arXiv.org, 2020-02</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>777,781</link.rule.ids></links><search><creatorcontrib>Dong, Zhe</creatorcontrib><creatorcontrib>Seybold, Bryan A</creatorcontrib><creatorcontrib>Murphy, Kevin P</creatorcontrib><creatorcontrib>Bui, Hung H</creatorcontrib><title>Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems</title><title>arXiv.org</title><description>We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.</description><subject>Continuity (mathematics)</subject><subject>Dynamical systems</subject><subject>Inference</subject><subject>Nonlinear dynamics</subject><subject>Nonlinear systems</subject><subject>Switching</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjrEKwjAURYMgWLT_EHAuxMTarFIVXVwqriXUV01Jk5qXIvr1ZvADnM4dDpczIQkXYpXJNeczkiJ2jDG-KXiei4RUpTNGDQg3uu2dD_oT11V5rYJ2Vhl6si14sA3Q1nlavXRoHtre6dlZoy0oT3dvq3rdRLd6Y4AeF2TaKoOQ_jgny8P-Uh6zwbvnCBjqzo0-nmPNBSukjH1S_Gd9AX2nQKY</recordid><startdate>20200210</startdate><enddate>20200210</enddate><creator>Dong, Zhe</creator><creator>Seybold, Bryan A</creator><creator>Murphy, Kevin P</creator><creator>Bui, Hung H</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200210</creationdate><title>Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems</title><author>Dong, Zhe ; Seybold, Bryan A ; Murphy, Kevin P ; Bui, Hung H</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23078823383</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Continuity (mathematics)</topic><topic>Dynamical systems</topic><topic>Inference</topic><topic>Nonlinear dynamics</topic><topic>Nonlinear systems</topic><topic>Switching</topic><toplevel>online_resources</toplevel><creatorcontrib>Dong, Zhe</creatorcontrib><creatorcontrib>Seybold, Bryan A</creatorcontrib><creatorcontrib>Murphy, Kevin P</creatorcontrib><creatorcontrib>Bui, Hung H</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dong, Zhe</au><au>Seybold, Bryan A</au><au>Murphy, Kevin P</au><au>Bui, Hung H</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems</atitle><jtitle>arXiv.org</jtitle><date>2020-02-10</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>We propose an efficient inference method for switching nonlinear dynamical systems. The key idea is to learn an inference network which can be used as a proposal distribution for the continuous latent variables, while performing exact marginalization of the discrete latent variables. This allows us to use the reparameterization trick, and apply end-to-end training with stochastic gradient descent. We show that the proposed method can successfully segment time series data, including videos and 3D human pose, into meaningful ``regimes'' by using the piece-wise nonlinear dynamics.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2307882338
source Free E- Journals
subjects Continuity (mathematics)
Dynamical systems
Inference
Nonlinear dynamics
Nonlinear systems
Switching
title Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T11%3A20%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Collapsed%20Amortized%20Variational%20Inference%20for%20Switching%20Nonlinear%20Dynamical%20Systems&rft.jtitle=arXiv.org&rft.au=Dong,%20Zhe&rft.date=2020-02-10&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2307882338%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2307882338&rft_id=info:pmid/&rfr_iscdi=true