Estimating Causal Effects with the Neural Autoregressive Density Estimator

TL;DR

This paper introduces a neural autoregressive density estimator approach to estimate causal effects in non-linear systems within Pearl's do-calculus framework, bypassing the need for explicit interaction modeling.

Contribution

It presents a novel method using neural autoregressive models for causal inference that handles non-linear relationships without explicit interaction modeling.

Findings

Successfully retrieves causal effects from synthetic non-linear data

Outperforms traditional linear models in causal effect estimation

Demonstrates flexibility in modeling complex causal systems

Abstract

Estimation of causal effects is fundamental in situations were the underlying system will be subject to active interventions. Part of building a causal inference engine is defining how variables relate to each other, that is, defining the functional relationship between variables given conditional dependencies. In this paper, we deviate from the common assumption of linear relationships in causal models by making use of neural autoregressive density estimators and use them to estimate causal effects within the Pearl's do-calculus framework. Using synthetic data, we show that the approach can retrieve causal effects from non-linear systems without explicitly modeling the interactions between the variables.