Sequential Likelihood-Free Inference with Neural Proposal

Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulation models on real-world datasets. As the likelihood evaluation is inaccessible, previous papers train the amortized neu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-11
Hauptverfasser: Kim, Dongjun, Song, Kyungwoo, Kim, YoonYeong, Shin, Yongjin, Kang, Wanmo, Il-Chul Moon, Joo, Weonyoung
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 Kim, Dongjun
Song, Kyungwoo
Kim, YoonYeong
Shin, Yongjin
Kang, Wanmo
Il-Chul Moon
Joo, Weonyoung
description Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulation models on real-world datasets. As the likelihood evaluation is inaccessible, previous papers train the amortized neural network to estimate the ground-truth posterior for the simulation of interest. Training the network and accumulating the dataset alternatively in a sequential manner could save the total simulation budget by orders of magnitude. In the data accumulation phase, the new simulation inputs are chosen within a portion of the total simulation budget to accumulate upon the collected dataset. This newly accumulated data degenerates because the set of simulation inputs is hardly mixed, and this degenerated data collection process ruins the posterior inference. This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i.i.d. sampling. The experiments show the improved performance of our sampler, especially for the simulations with multi-modal posteriors.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2451458174</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2451458174</sourcerecordid><originalsourceid>FETCH-proquest_journals_24514581743</originalsourceid><addsrcrecordid>eNqNjEsKwjAUAIMgWLR3CLgOpPnYuhaLgoig-xLqK00NSc0Hr28WHsDVLGaYBSoY5xVpBGMrVIYwUUrZrmZS8gLt7_BOYKNWBl_0C4wenXuS1gPgsx3Ag-0Bf3Qc8RWSz9XNu9kFZTZoOSgToPxxjbbt8XE4kdm7vAyxm1zyNquOCVkJ2VS14P9VX4uINoA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2451458174</pqid></control><display><type>article</type><title>Sequential Likelihood-Free Inference with Neural Proposal</title><source>Free E- Journals</source><creator>Kim, Dongjun ; Song, Kyungwoo ; Kim, YoonYeong ; Shin, Yongjin ; Kang, Wanmo ; Il-Chul Moon ; Joo, Weonyoung</creator><creatorcontrib>Kim, Dongjun ; Song, Kyungwoo ; Kim, YoonYeong ; Shin, Yongjin ; Kang, Wanmo ; Il-Chul Moon ; Joo, Weonyoung</creatorcontrib><description>Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulation models on real-world datasets. As the likelihood evaluation is inaccessible, previous papers train the amortized neural network to estimate the ground-truth posterior for the simulation of interest. Training the network and accumulating the dataset alternatively in a sequential manner could save the total simulation budget by orders of magnitude. In the data accumulation phase, the new simulation inputs are chosen within a portion of the total simulation budget to accumulate upon the collected dataset. This newly accumulated data degenerates because the set of simulation inputs is hardly mixed, and this degenerated data collection process ruins the posterior inference. This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i.i.d. sampling. The experiments show the improved performance of our sampler, especially for the simulations with multi-modal posteriors.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Bayesian analysis ; Density ; Markov chains ; Sampling methods ; Simulation ; Statistical inference</subject><ispartof>arXiv.org, 2022-11</ispartof><rights>2022. 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>780,784</link.rule.ids></links><search><creatorcontrib>Kim, Dongjun</creatorcontrib><creatorcontrib>Song, Kyungwoo</creatorcontrib><creatorcontrib>Kim, YoonYeong</creatorcontrib><creatorcontrib>Shin, Yongjin</creatorcontrib><creatorcontrib>Kang, Wanmo</creatorcontrib><creatorcontrib>Il-Chul Moon</creatorcontrib><creatorcontrib>Joo, Weonyoung</creatorcontrib><title>Sequential Likelihood-Free Inference with Neural Proposal</title><title>arXiv.org</title><description>Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulation models on real-world datasets. As the likelihood evaluation is inaccessible, previous papers train the amortized neural network to estimate the ground-truth posterior for the simulation of interest. Training the network and accumulating the dataset alternatively in a sequential manner could save the total simulation budget by orders of magnitude. In the data accumulation phase, the new simulation inputs are chosen within a portion of the total simulation budget to accumulate upon the collected dataset. This newly accumulated data degenerates because the set of simulation inputs is hardly mixed, and this degenerated data collection process ruins the posterior inference. This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i.i.d. sampling. The experiments show the improved performance of our sampler, especially for the simulations with multi-modal posteriors.</description><subject>Algorithms</subject><subject>Bayesian analysis</subject><subject>Density</subject><subject>Markov chains</subject><subject>Sampling methods</subject><subject>Simulation</subject><subject>Statistical inference</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjEsKwjAUAIMgWLR3CLgOpPnYuhaLgoig-xLqK00NSc0Hr28WHsDVLGaYBSoY5xVpBGMrVIYwUUrZrmZS8gLt7_BOYKNWBl_0C4wenXuS1gPgsx3Ag-0Bf3Qc8RWSz9XNu9kFZTZoOSgToPxxjbbt8XE4kdm7vAyxm1zyNquOCVkJ2VS14P9VX4uINoA</recordid><startdate>20221104</startdate><enddate>20221104</enddate><creator>Kim, Dongjun</creator><creator>Song, Kyungwoo</creator><creator>Kim, YoonYeong</creator><creator>Shin, Yongjin</creator><creator>Kang, Wanmo</creator><creator>Il-Chul Moon</creator><creator>Joo, Weonyoung</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>PTHSS</scope></search><sort><creationdate>20221104</creationdate><title>Sequential Likelihood-Free Inference with Neural Proposal</title><author>Kim, Dongjun ; Song, Kyungwoo ; Kim, YoonYeong ; Shin, Yongjin ; Kang, Wanmo ; Il-Chul Moon ; Joo, Weonyoung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24514581743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Bayesian analysis</topic><topic>Density</topic><topic>Markov chains</topic><topic>Sampling methods</topic><topic>Simulation</topic><topic>Statistical inference</topic><toplevel>online_resources</toplevel><creatorcontrib>Kim, Dongjun</creatorcontrib><creatorcontrib>Song, Kyungwoo</creatorcontrib><creatorcontrib>Kim, YoonYeong</creatorcontrib><creatorcontrib>Shin, Yongjin</creatorcontrib><creatorcontrib>Kang, Wanmo</creatorcontrib><creatorcontrib>Il-Chul Moon</creatorcontrib><creatorcontrib>Joo, Weonyoung</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>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kim, Dongjun</au><au>Song, Kyungwoo</au><au>Kim, YoonYeong</au><au>Shin, Yongjin</au><au>Kang, Wanmo</au><au>Il-Chul Moon</au><au>Joo, Weonyoung</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Sequential Likelihood-Free Inference with Neural Proposal</atitle><jtitle>arXiv.org</jtitle><date>2022-11-04</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Bayesian inference without the likelihood evaluation, or likelihood-free inference, has been a key research topic in simulation studies for gaining quantitatively validated simulation models on real-world datasets. As the likelihood evaluation is inaccessible, previous papers train the amortized neural network to estimate the ground-truth posterior for the simulation of interest. Training the network and accumulating the dataset alternatively in a sequential manner could save the total simulation budget by orders of magnitude. In the data accumulation phase, the new simulation inputs are chosen within a portion of the total simulation budget to accumulate upon the collected dataset. This newly accumulated data degenerates because the set of simulation inputs is hardly mixed, and this degenerated data collection process ruins the posterior inference. This paper introduces a new sampling approach, called Neural Proposal (NP), of the simulation input that resolves the biased data collection as it guarantees the i.i.d. sampling. The experiments show the improved performance of our sampler, especially for the simulations with multi-modal posteriors.</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, 2022-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2451458174
source Free E- Journals
subjects Algorithms
Bayesian analysis
Density
Markov chains
Sampling methods
Simulation
Statistical inference
title Sequential Likelihood-Free Inference with Neural Proposal
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T19%3A42%3A00IST&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=Sequential%20Likelihood-Free%20Inference%20with%20Neural%20Proposal&rft.jtitle=arXiv.org&rft.au=Kim,%20Dongjun&rft.date=2022-11-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2451458174%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2451458174&rft_id=info:pmid/&rfr_iscdi=true