Robust Estimation of Causal Heteroscedastic Noise Models

Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tran, Quang-Duy, Duong, Bao, Nguyen, Phuoc, Nguyen, Thin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Tran, Quang-Duy
Duong, Bao
Nguyen, Phuoc
Nguyen, Thin
description Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal direction after estimating the model in each direction. The heteroscedastic noise model is a type of structural causal model where the cause can contribute to both the mean and variance of the noise. Current methods for estimating heteroscedastic noise models choose the Gaussian likelihood as the optimization objective which can be suboptimal and unstable when the data has a non-Gaussian distribution. To address this limitation, we propose a novel approach to estimating this model with Student's $t$-distribution, which is known for its robustness in accounting for sampling variability with smaller sample sizes and extreme values without significantly altering the overall distribution shape. This adaptability is beneficial for capturing the parameters of the noise distribution in heteroscedastic noise models. Our empirical evaluations demonstrate that our estimators are more robust and achieve better overall performance across synthetic and real benchmarks.
doi_str_mv 10.48550/arxiv.2312.10102
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2312_10102</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2312_10102</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-db4257cc05bbf879d48ea7ce5ee4a7883c877223b7e4f3ddc205993296c8d3e23</originalsourceid><addsrcrecordid>eNotj7FqwzAURbV0KGk-oFP0A3blJ8mSx2DcpJCmULKbJ-kZDE5ULKckf1_X7XSHA5dzGHsuRK6s1uIFx1v_nYMsIC9EIeCR2c_ormniTZr6M059vPDY8RqvCQe-p4nGmDwFnLHnx9gn4u8x0JCe2EOHQ6L1_67Y6bU51fvs8LF7q7eHDEsDWXAKtPFeaOc6a6qgLKHxpIkUGmult8YASGdIdTIED0JXlYSq9DZIArlim7_bRb39GmfL8d7-JrRLgvwBqVZA7Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Robust Estimation of Causal Heteroscedastic Noise Models</title><source>arXiv.org</source><creator>Tran, Quang-Duy ; Duong, Bao ; Nguyen, Phuoc ; Nguyen, Thin</creator><creatorcontrib>Tran, Quang-Duy ; Duong, Bao ; Nguyen, Phuoc ; Nguyen, Thin</creatorcontrib><description>Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal direction after estimating the model in each direction. The heteroscedastic noise model is a type of structural causal model where the cause can contribute to both the mean and variance of the noise. Current methods for estimating heteroscedastic noise models choose the Gaussian likelihood as the optimization objective which can be suboptimal and unstable when the data has a non-Gaussian distribution. To address this limitation, we propose a novel approach to estimating this model with Student's $t$-distribution, which is known for its robustness in accounting for sampling variability with smaller sample sizes and extreme values without significantly altering the overall distribution shape. This adaptability is beneficial for capturing the parameters of the noise distribution in heteroscedastic noise models. Our empirical evaluations demonstrate that our estimators are more robust and achieve better overall performance across synthetic and real benchmarks.</description><identifier>DOI: 10.48550/arxiv.2312.10102</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2023-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2312.10102$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2312.10102$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Tran, Quang-Duy</creatorcontrib><creatorcontrib>Duong, Bao</creatorcontrib><creatorcontrib>Nguyen, Phuoc</creatorcontrib><creatorcontrib>Nguyen, Thin</creatorcontrib><title>Robust Estimation of Causal Heteroscedastic Noise Models</title><description>Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal direction after estimating the model in each direction. The heteroscedastic noise model is a type of structural causal model where the cause can contribute to both the mean and variance of the noise. Current methods for estimating heteroscedastic noise models choose the Gaussian likelihood as the optimization objective which can be suboptimal and unstable when the data has a non-Gaussian distribution. To address this limitation, we propose a novel approach to estimating this model with Student's $t$-distribution, which is known for its robustness in accounting for sampling variability with smaller sample sizes and extreme values without significantly altering the overall distribution shape. This adaptability is beneficial for capturing the parameters of the noise distribution in heteroscedastic noise models. Our empirical evaluations demonstrate that our estimators are more robust and achieve better overall performance across synthetic and real benchmarks.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7FqwzAURbV0KGk-oFP0A3blJ8mSx2DcpJCmULKbJ-kZDE5ULKckf1_X7XSHA5dzGHsuRK6s1uIFx1v_nYMsIC9EIeCR2c_ormniTZr6M059vPDY8RqvCQe-p4nGmDwFnLHnx9gn4u8x0JCe2EOHQ6L1_67Y6bU51fvs8LF7q7eHDEsDWXAKtPFeaOc6a6qgLKHxpIkUGmult8YASGdIdTIED0JXlYSq9DZIArlim7_bRb39GmfL8d7-JrRLgvwBqVZA7Q</recordid><startdate>20231214</startdate><enddate>20231214</enddate><creator>Tran, Quang-Duy</creator><creator>Duong, Bao</creator><creator>Nguyen, Phuoc</creator><creator>Nguyen, Thin</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20231214</creationdate><title>Robust Estimation of Causal Heteroscedastic Noise Models</title><author>Tran, Quang-Duy ; Duong, Bao ; Nguyen, Phuoc ; Nguyen, Thin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-db4257cc05bbf879d48ea7ce5ee4a7883c877223b7e4f3ddc205993296c8d3e23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Tran, Quang-Duy</creatorcontrib><creatorcontrib>Duong, Bao</creatorcontrib><creatorcontrib>Nguyen, Phuoc</creatorcontrib><creatorcontrib>Nguyen, Thin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tran, Quang-Duy</au><au>Duong, Bao</au><au>Nguyen, Phuoc</au><au>Nguyen, Thin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust Estimation of Causal Heteroscedastic Noise Models</atitle><date>2023-12-14</date><risdate>2023</risdate><abstract>Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this problem is assuming that cause and effect are generated from a structural causal model, enabling identification of the causal direction after estimating the model in each direction. The heteroscedastic noise model is a type of structural causal model where the cause can contribute to both the mean and variance of the noise. Current methods for estimating heteroscedastic noise models choose the Gaussian likelihood as the optimization objective which can be suboptimal and unstable when the data has a non-Gaussian distribution. To address this limitation, we propose a novel approach to estimating this model with Student's $t$-distribution, which is known for its robustness in accounting for sampling variability with smaller sample sizes and extreme values without significantly altering the overall distribution shape. This adaptability is beneficial for capturing the parameters of the noise distribution in heteroscedastic noise models. Our empirical evaluations demonstrate that our estimators are more robust and achieve better overall performance across synthetic and real benchmarks.</abstract><doi>10.48550/arxiv.2312.10102</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2312.10102
ispartof
issn
language eng
recordid cdi_arxiv_primary_2312_10102
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title Robust Estimation of Causal Heteroscedastic Noise Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T20%3A34%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Robust%20Estimation%20of%20Causal%20Heteroscedastic%20Noise%20Models&rft.au=Tran,%20Quang-Duy&rft.date=2023-12-14&rft_id=info:doi/10.48550/arxiv.2312.10102&rft_dat=%3Carxiv_GOX%3E2312_10102%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true