Saved in:
Bibliographic Details
Main Authors: Nguyen, Nghia D., Robles-Granda, Pablo, Varshney, Lav R.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.11565
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914387569147904
author Nguyen, Nghia D.
Robles-Granda, Pablo
Varshney, Lav R.
author_facet Nguyen, Nghia D.
Robles-Granda, Pablo
Varshney, Lav R.
contents Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses a significant challenge in achieving accurate and efficient estimation. We introduce causal autoencoding and treatment conditioning (CAETC), a novel method for this problem. Built on adversarial representation learning, our method leverages an autoencoding architecture to learn a partially invertible and treatment-invariant representation, where the outcome prediction task is cast as applying a treatment-specific conditioning on the representation. Our design is independent of the underlying sequence model and can be applied to existing architectures such as long short-term memories (LSTMs) or temporal convolution networks (TCNs). We conduct extensive experiments on synthetic, semi-synthetic, and real-world data to demonstrate that CAETC yields significant improvement in counterfactual estimation over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11565
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time
Nguyen, Nghia D.
Robles-Granda, Pablo
Varshney, Lav R.
Machine Learning
Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses a significant challenge in achieving accurate and efficient estimation. We introduce causal autoencoding and treatment conditioning (CAETC), a novel method for this problem. Built on adversarial representation learning, our method leverages an autoencoding architecture to learn a partially invertible and treatment-invariant representation, where the outcome prediction task is cast as applying a treatment-specific conditioning on the representation. Our design is independent of the underlying sequence model and can be applied to existing architectures such as long short-term memories (LSTMs) or temporal convolution networks (TCNs). We conduct extensive experiments on synthetic, semi-synthetic, and real-world data to demonstrate that CAETC yields significant improvement in counterfactual estimation over existing methods.
title CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time
topic Machine Learning
url https://arxiv.org/abs/2603.11565