Adversarial Orthogonal Regression: Two non-Linear Regressions for Causal Inference

09/10/2019
by   M. Reza Heydari, et al.
0

We propose two nonlinear regression methods, named Adversarial Orthogonal Regression (AdOR) for additive noise models and Adversarial Orthogonal Structural Equation Model (AdOSE) for the general case of structural equation models. Both methods try to make the residual of regression independent from regressors while putting no assumption on noise distribution. In both methods, two adversarial networks are trained simultaneously where a regression network outputs predictions and a loss network that estimates mutual information (in AdOR) and KL-divergence (in AdOSE). These methods can be formulated as a minimax two-player game; at equilibrium, AdOR finds a deterministic map between inputs and output and estimates mutual information between residual and inputs, while AdOSE estimates a conditional probability distribution of output given inputs. The proposed methods can be used as subroutines to address several learning problems in causality, such as causal direction determination (or more generally, causal structure learning) and causal model estimation. Synthetic and real-world experiments demonstrate that the proposed methods have a remarkable performance with respect to previous solutions.

READ FULL TEXT
research
03/29/2011

Least-Squares Independence Regression for Non-Linear Causal Inference under Non-Gaussian Noise

The discovery of non-linear causal relationship under additive non-Gauss...
research
07/21/2012

Causal Inference on Time Series using Structural Equation Models

Causal inference uses observations to infer the causal structure of the ...
research
11/13/2017

On the boundary between qualitative and quantitative methods for causal inference

We consider how to quantify the causal effect from a random variable to ...
research
12/23/2020

Causal Inference Using Linear Time-Varying Filters with Additive Noise

Causal inference using the restricted structural causal model framework ...
research
08/10/2021

Causal Order Identification to Address Confounding: Binary Variables

This paper considers an extension of the linear non-Gaussian acyclic mod...
research
08/08/2023

SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modeling

Causal inference is a crucial goal of science, enabling researchers to a...

Please sign up or login with your details

Forgot password? Click here to reset