# A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Models

arXiv: https://arxiv.org/abs/2102.06648 · HTML: https://mlsanity.com/paper/2102.06648/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 14 of 14)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder](https://mlsanity.com/paper/1609.08816/) (2016)
- [Lagging Inference Networks and Posterior Collapse in Variational Autoencoders](https://mlsanity.com/paper/1901.05534/) (2019)
- [Preventing Posterior Collapse with delta-VAEs](https://mlsanity.com/paper/1901.03416/) (2019)
- [Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models](https://mlsanity.com/paper/2007.00163/) (2020)
- [The Usual Suspects? Reassessing Blame for VAE Posterior Collapse](https://mlsanity.com/paper/1912.10702/) (2019)
- [Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data](https://mlsanity.com/paper/1809.02519/) (2018)
- [Counterfactual Reasoning for Fair Clinical Risk Prediction](https://mlsanity.com/paper/1907.06260/) (2019)
- [Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects](https://mlsanity.com/paper/1808.03333/) (2018)
- [MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models](https://mlsanity.com/paper/2002.10837/) (2020)

## Built on by (most cited first, 29 of 29)

- [Measuring axiomatic soundness of counterfactual image models](https://mlsanity.com/paper/2303.01274/) (2023)
- [Conceptualizing Treatment Leakage in Text-based Causal Inference](https://mlsanity.com/paper/2205.00465/) (2022)
- [Adapting to Latent Subgroup Shifts via Concepts and Proxies](https://mlsanity.com/paper/2212.11254/) (2022)
- [Conformal Convolution and Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects](https://mlsanity.com/paper/2402.04906/) (2024)
- [DeCaFlow: A deconfounding causal generative model](https://mlsanity.com/paper/2503.15114/) (2025)
- [Estimating Causal Effects using a Multi-task Deep Ensemble](https://mlsanity.com/paper/2301.11351/) (2023)
- [Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding](https://mlsanity.com/paper/2306.01157/) (2023)
- [Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing](https://mlsanity.com/paper/2401.15447/) (2024)
- [Causal Inference with Conditional Instruments using Deep Generative Models](https://mlsanity.com/paper/2211.16246/) (2022)
- [Proxy Methods for Domain Adaptation](https://mlsanity.com/paper/2403.07442/) (2024)
- [Disentangled Representation Learning for Causal Inference with Instruments](https://mlsanity.com/paper/2412.04641/) (2024)
- [Time Series Causal Link Estimation under Hidden Confounding using Knockoff Interventions](https://mlsanity.com/paper/2209.11497/) (2022)
- [Kernel Single Proxy Control for Deterministic Confounding](https://mlsanity.com/paper/2308.04585/) (2023)
- [Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning](https://mlsanity.com/paper/2412.05783/) (2024)
- [Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportability](https://mlsanity.com/paper/2502.20153/) (2025)
- [SBI: A Simulation-Based Test of Identifiability for Bayesian Causal Inference](https://mlsanity.com/paper/2102.11761/) (2021)
- [Causal Inference from Small High-dimensional Datasets](https://mlsanity.com/paper/2205.09281/) (2022)
- [Causal Deep Reinforcement Learning Using Observational Data](https://mlsanity.com/paper/2211.15355/) (2022)
- [High Dimensional Causal Inference with Variational Backdoor Adjustment](https://mlsanity.com/paper/2310.06100/) (2023)
- [PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect](https://mlsanity.com/paper/2406.03864/) (2024)
- [Confounder Balancing for Instrumental Variable Regression with Latent Variable](https://mlsanity.com/paper/2211.10008/) (2022)
- [Active and Passive Causal Inference Learning](https://mlsanity.com/paper/2308.09248/) (2023)
- [Multi-treatment Effect Estimation from Biomedical Data](https://mlsanity.com/paper/2112.07574/) (2021)
- [Identifiable causal inference with noisy treatment and no side information](https://mlsanity.com/paper/2306.10614/) (2023)
- [Estimating Individual Dose-Response Curves under Unobserved Confounders from Observational Data](https://mlsanity.com/paper/2410.15706/) (2024)
- [Coupling Generative Modeling and an Autoencoder with the Causal Bridge](https://mlsanity.com/paper/2509.25599/) (2025)
- [PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimation](https://mlsanity.com/paper/2512.18737/) (2025)
- [Uncertainty-Guided LLM Semantic Augmentation for Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2607.26599/) (2026)
- [Proximal Balancing for Causal Effect Estimation under Unmeasured Confounding](https://mlsanity.com/paper/2609.40051/) (2026)

## Abstract (arXiv)

Using deep latent variable models in causal inference has attracted considerable interest recently, but an essential open question is their ability to yield consistent causal estimates. While they have demonstrated promising results and theory exists on some simple model formulations, we also know that causal effects are not even identifiable in general with latent variables. We investigate this gap between theory and empirical results with analytical considerations and extensive experiments under multiple synthetic and real-world data sets, using the causal effect variational autoencoder (CEVAE) as a case study. While CEVAE seems to work reliably under some simple scenarios, it does not estimate the causal effect correctly with a misspecified latent variable or a complex data distribution, as opposed to its original motivation. Hence, our results show that more attention should be paid to ensuring the correctness of causal estimates with deep latent variable models.