Learning Sparse Nonparametric DAGs

Abstract

We develop a framework for learning sparse nonparametric directed acyclic graphs (DAGs) from data. Our approach is based on a recent algebraic characterization of DAGs that led to a fully continuous program for score-based learning of DAG models parametrized by a linear structural equation model (SEM). We extend this algebraic characterization to nonparametric SEM by leveraging nonparametric sparsity based on partial derivatives, resulting in a continuous optimization problem that can be applied to a variety of nonparametric and semiparametric models including GLMs, additive noise models, and index models as special cases. Unlike existing approaches that require specific modeling choices, loss functions, or algorithms, we present a completely general framework that can be applied to general nonlinear models (e.g. without additive noise), general differentiable loss functions, and generic black-box optimization routines. The code is available at https://github.com/xunzheng/notears.

arXiv commentTo appear in AISTATS 2020

References in corpus (20)

• Counterfactual Fairness
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Distinguishing cause from effect using observational data: methods and benchmarks
• On the Identifiability of the Post-Nonlinear Causal Model
• CAM: Causal additive models, high-dimensional order search and penalized regression
• Identifiability of Gaussian structural equation models with equal error variances
• DAGs with NO TEARS: Continuous Optimization for Structure Learning
• DAG-GNN: DAG Structure Learning with Graph Neural Networks
• High-dimensional learning of linear causal networks via inverse covariance estimation
• Nonparametric sparsity and regularization
• Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification
• Sparse single-index model
• On Causal Discovery with Equal Variance Assumption
• Selection of variables and dimension reduction in high-dimensional non-parametric regression
• A Spectral Series Approach to High-Dimensional Nonparametric Regression
• Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
• Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
• Gradient-Based Neural DAG Learning
• Learning Quadratic Variance Function (QVF) DAG models via OverDispersion Scoring (ODS)
• Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery

Cited by in corpus (8)

• Causality in cognitive neuroscience: concepts, challenges, and distributional robustness
• CASTLE: Regularization via Auxiliary Causal Graph Discovery
• Differentiable Causal Discovery from Interventional Data
• Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data
• Ordering-Based Causal Discovery with Reinforcement Learning
• Efficient Neural Causal Discovery without Acyclicity Constraints
• Efficient and Scalable Structure Learning for Bayesian Networks: Algorithms and Applications
• Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG