Recovering Latent Confounders from High-dimensional Proxy Variables ...
Detecting latent confounders from proxy variables is an essential problem in causal effect estimation. Previous approaches are limited to low-dimensional proxies, sorted proxies, and binary treatments. We remove these assumptions and present a novel Proxy Confounder Factorization (PCF) framework for...
Main Authors: | , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2024
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2403.14228 https://arxiv.org/abs/2403.14228 |
id |
ftdatacite:10.48550/arxiv.2403.14228 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2403.14228 2024-04-28T08:30:30+00:00 Recovering Latent Confounders from High-dimensional Proxy Variables ... Mankovich, Nathan Durand, Homer Diaz, Emiliano Varando, Gherardo Camps-Valls, Gustau 2024 https://dx.doi.org/10.48550/arxiv.2403.14228 https://arxiv.org/abs/2403.14228 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Machine Learning stat.ML Machine Learning cs.LG FOS Computer and information sciences article Article Preprint CreativeWork 2024 ftdatacite https://doi.org/10.48550/arxiv.2403.14228 2024-04-02T11:56:27Z Detecting latent confounders from proxy variables is an essential problem in causal effect estimation. Previous approaches are limited to low-dimensional proxies, sorted proxies, and binary treatments. We remove these assumptions and present a novel Proxy Confounder Factorization (PCF) framework for continuous treatment effect estimation when latent confounders manifest through high-dimensional, mixed proxy variables. For specific sample sizes, our two-step PCF implementation, using Independent Component Analysis (ICA-PCF), and the end-to-end implementation, using Gradient Descent (GD-PCF), achieve high correlation with the latent confounder and low absolute error in causal effect estimation with synthetic datasets in the high sample size regime. Even when faced with climate data, ICA-PCF recovers four components that explain $75.9\%$ of the variance in the North Atlantic Oscillation, a known confounder of precipitation patterns in Europe. Code for our PCF implementations and experiments can be found here: ... Article in Journal/Newspaper North Atlantic North Atlantic oscillation DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Machine Learning stat.ML Machine Learning cs.LG FOS Computer and information sciences |
spellingShingle |
Machine Learning stat.ML Machine Learning cs.LG FOS Computer and information sciences Mankovich, Nathan Durand, Homer Diaz, Emiliano Varando, Gherardo Camps-Valls, Gustau Recovering Latent Confounders from High-dimensional Proxy Variables ... |
topic_facet |
Machine Learning stat.ML Machine Learning cs.LG FOS Computer and information sciences |
description |
Detecting latent confounders from proxy variables is an essential problem in causal effect estimation. Previous approaches are limited to low-dimensional proxies, sorted proxies, and binary treatments. We remove these assumptions and present a novel Proxy Confounder Factorization (PCF) framework for continuous treatment effect estimation when latent confounders manifest through high-dimensional, mixed proxy variables. For specific sample sizes, our two-step PCF implementation, using Independent Component Analysis (ICA-PCF), and the end-to-end implementation, using Gradient Descent (GD-PCF), achieve high correlation with the latent confounder and low absolute error in causal effect estimation with synthetic datasets in the high sample size regime. Even when faced with climate data, ICA-PCF recovers four components that explain $75.9\%$ of the variance in the North Atlantic Oscillation, a known confounder of precipitation patterns in Europe. Code for our PCF implementations and experiments can be found here: ... |
format |
Article in Journal/Newspaper |
author |
Mankovich, Nathan Durand, Homer Diaz, Emiliano Varando, Gherardo Camps-Valls, Gustau |
author_facet |
Mankovich, Nathan Durand, Homer Diaz, Emiliano Varando, Gherardo Camps-Valls, Gustau |
author_sort |
Mankovich, Nathan |
title |
Recovering Latent Confounders from High-dimensional Proxy Variables ... |
title_short |
Recovering Latent Confounders from High-dimensional Proxy Variables ... |
title_full |
Recovering Latent Confounders from High-dimensional Proxy Variables ... |
title_fullStr |
Recovering Latent Confounders from High-dimensional Proxy Variables ... |
title_full_unstemmed |
Recovering Latent Confounders from High-dimensional Proxy Variables ... |
title_sort |
recovering latent confounders from high-dimensional proxy variables ... |
publisher |
arXiv |
publishDate |
2024 |
url |
https://dx.doi.org/10.48550/arxiv.2403.14228 https://arxiv.org/abs/2403.14228 |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2403.14228 |
_version_ |
1797588352735641600 |