TRADE: Transfer of Distributions between External Conditions with Normalizing Flows
Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as t...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-10 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
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 | Wahl, Stefan Rousselot, Armand Draxler, Felix Köthe, Ullrich |
description | Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on backward training, which is prone to unstable training. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d. samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3121360272</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3121360272</sourcerecordid><originalsourceid>FETCH-proquest_journals_31213602723</originalsourceid><addsrcrecordid>eNqNjMEKgkAUAJcgSMp_eNBZ0Lep0S3U6NShvMtKa61su7VvxejrI-oDOs1hhpmwADlPovUKccZCoj6OY8xyTFMesFN93JbVBmonDHXSge2gVOSdagevrCFopR-lNFA9vXRGaCisOauvG5W_wsG6m9DqpcwFdtqOtGDTTmiS4Y9zttxVdbGP7s4-Bkm-6e3wWVHDE0x4FmOO_L_qDRN-P_0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3121360272</pqid></control><display><type>article</type><title>TRADE: Transfer of Distributions between External Conditions with Normalizing Flows</title><source>Free E- Journals</source><creator>Wahl, Stefan ; Rousselot, Armand ; Draxler, Felix ; Köthe, Ullrich</creator><creatorcontrib>Wahl, Stefan ; Rousselot, Armand ; Draxler, Felix ; Köthe, Ullrich</creatorcontrib><description>Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on backward training, which is prone to unstable training. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d. samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Bayesian analysis ; Boundary value problems ; Neural networks ; Parameters ; Statistical inference</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>776,780</link.rule.ids></links><search><creatorcontrib>Wahl, Stefan</creatorcontrib><creatorcontrib>Rousselot, Armand</creatorcontrib><creatorcontrib>Draxler, Felix</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><title>TRADE: Transfer of Distributions between External Conditions with Normalizing Flows</title><title>arXiv.org</title><description>Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on backward training, which is prone to unstable training. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d. samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models.</description><subject>Bayesian analysis</subject><subject>Boundary value problems</subject><subject>Neural networks</subject><subject>Parameters</subject><subject>Statistical inference</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNjMEKgkAUAJcgSMp_eNBZ0Lep0S3U6NShvMtKa61su7VvxejrI-oDOs1hhpmwADlPovUKccZCoj6OY8xyTFMesFN93JbVBmonDHXSge2gVOSdagevrCFopR-lNFA9vXRGaCisOauvG5W_wsG6m9DqpcwFdtqOtGDTTmiS4Y9zttxVdbGP7s4-Bkm-6e3wWVHDE0x4FmOO_L_qDRN-P_0</recordid><startdate>20241025</startdate><enddate>20241025</enddate><creator>Wahl, Stefan</creator><creator>Rousselot, Armand</creator><creator>Draxler, Felix</creator><creator>Köthe, Ullrich</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>20241025</creationdate><title>TRADE: Transfer of Distributions between External Conditions with Normalizing Flows</title><author>Wahl, Stefan ; Rousselot, Armand ; Draxler, Felix ; Köthe, Ullrich</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31213602723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Bayesian analysis</topic><topic>Boundary value problems</topic><topic>Neural networks</topic><topic>Parameters</topic><topic>Statistical inference</topic><toplevel>online_resources</toplevel><creatorcontrib>Wahl, Stefan</creatorcontrib><creatorcontrib>Rousselot, Armand</creatorcontrib><creatorcontrib>Draxler, Felix</creatorcontrib><creatorcontrib>Köthe, Ullrich</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest 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>Wahl, Stefan</au><au>Rousselot, Armand</au><au>Draxler, Felix</au><au>Köthe, Ullrich</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>TRADE: Transfer of Distributions between External Conditions with Normalizing Flows</atitle><jtitle>arXiv.org</jtitle><date>2024-10-25</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Modeling distributions that depend on external control parameters is a common scenario in diverse applications like molecular simulations, where system properties like temperature affect molecular configurations. Despite the relevance of these applications, existing solutions are unsatisfactory as they require severely restricted model architectures or rely on backward training, which is prone to unstable training. We introduce TRADE, which overcomes these limitations by formulating the learning process as a boundary value problem. By initially training the model for a specific condition using either i.i.d. samples or backward KL training, we establish a boundary distribution. We then propagate this information across other conditions using the gradient of the unnormalized density with respect to the external parameter. This formulation, akin to the principles of physics-informed neural networks, allows us to efficiently learn parameter-dependent distributions without restrictive assumptions. Experimentally, we demonstrate that TRADE achieves excellent results in a wide range of applications, ranging from Bayesian inference and molecular simulations to physical lattice models.</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, 2024-10 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3121360272 |
source | Free E- Journals |
subjects | Bayesian analysis Boundary value problems Neural networks Parameters Statistical inference |
title | TRADE: Transfer of Distributions between External Conditions with Normalizing Flows |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T15%3A19%3A22IST&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=TRADE:%20Transfer%20of%20Distributions%20between%20External%20Conditions%20with%20Normalizing%20Flows&rft.jtitle=arXiv.org&rft.au=Wahl,%20Stefan&rft.date=2024-10-25&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3121360272%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3121360272&rft_id=info:pmid/&rfr_iscdi=true |