The Causal Neural Connection: Expressiveness, Learnability, and Inference

07/02/2021
by   Kevin Xia, et al.
35

One of the central elements of any causal inference is an object called structural causal model (SCM), which represents a collection of mechanisms and exogenous sources of random variation of the system under investigation (Pearl, 2000). An important property of many kinds of neural networks is universal approximability: the ability to approximate any function to arbitrary precision. Given this property, one may be tempted to surmise that a collection of neural nets is capable of learning any SCM by training on data generated by that SCM. In this paper, we show this is not the case by disentangling the notions of expressivity and learnability. Specifically, we show that the causal hierarchy theorem (Thm. 1, Bareinboim et al., 2020), which describes the limits of what can be learned from data, still holds for neural models. For instance, an arbitrarily complex and expressive neural net is unable to predict the effects of interventions given observational data alone. Given this result, we introduce a special type of SCM called a neural causal model (NCM), and formalize a new type of inductive bias to encode structural constraints necessary for performing causal inferences. Building on this new class of models, we focus on solving two canonical tasks found in the literature known as causal identification and estimation. Leveraging the neural toolbox, we develop an algorithm that is both sufficient and necessary to determine whether a causal effect can be learned from data (i.e., causal identifiability); it then estimates the effect whenever identifiability holds (causal estimation). Simulations corroborate the proposed approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/29/2019

Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets

One of the most common mistakes made when performing data analysis is at...
research
09/09/2021

Relating Graph Neural Networks to Structural Causal Models

Causality can be described in terms of a structural causal model (SCM) t...
research
08/02/2020

Structural Causal Models Are (Solvable by) Credal Networks

A structural causal model is made of endogenous (manifest) and exogenous...
research
02/22/2022

Effect Identification in Cluster Causal Diagrams

One pervasive task found throughout the empirical sciences is to determi...
research
12/15/2018

Causal Identification under Markov Equivalence

Assessing the magnitude of cause-and-effect relations is one of the cent...
research
08/17/2022

Revisiting the propensity score's central role: Towards bridging balance and efficiency in the era of causal machine learning

About forty years ago, in a now–seminal contribution, Rosenbaum Rubi...
research
07/07/2021

Nested Counterfactual Identification from Arbitrary Surrogate Experiments

The Ladder of Causation describes three qualitatively different types of...

Please sign up or login with your details

Forgot password? Click here to reset