CAM: Causal additive models, high-dimensional order search and penalized regression
arXiv:1310.1533 · doi:10.1214/14-AOS1260
Abstract
We develop estimation for potentially high-dimensional additive structural equation models. A key component of our approach is to decouple order search among the variables from feature or edge selection in a directed acyclic graph encoding the causal structure. We show that the former can be done with nonregularized (restricted) maximum likelihood estimation while the latter can be efficiently addressed using sparse regression techniques. Thus, we substantially simplify the problem of structure search and estimation for an important class of causal models. We establish consistency of the (restricted) maximum likelihood estimator for low- and high-dimensional scenarios, and we also allow for misspecification of the error distribution. Furthermore, we develop an efficient computational algorithm which can deal with many variables, and the new method's accuracy and performance is illustrated on simulated and real data.
arXiv commentPublished in at http://dx.doi.org/10.1214/14-AOS1260 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (20)
- High-dimensional graphs and variable selection with the Lasso
- Boosting Algorithms: Regularization, Prediction and Model Fitting
- The sparsity and bias of the Lasso selection in high-dimensional linear regression
- High-dimensional additive modeling
- Learning high-dimensional directed acyclic graphs with latent and selection variables
- On the Identifiability of the Post-Nonlinear Causal Model
- Identifiability of Gaussian structural equation models with equal error variances
- Causal Discovery with Continuous Additive Noise Models
- Directed Cyclic Graphical Representations of Feedback Models
- A Discovery Algorithm for Directed Cyclic Graphs
- Ordering-Based Search: A Simple and Effective Algorithm for Learning Bayesian Networks
- -penalized maximum likelihood for sparse directed acyclic graphs
- High-dimensional learning of linear causal networks via inverse covariance estimation
- Adjacency-Faithfulness and Conservative Causal Inference
- Identifying confounders using additive noise models
- A simple smooth backfitting method for additive models
- Score-based Causal Learning in Additive Noise Models
- Cyclic Causal Discovery from Continuous Equilibrium Data
- Learning Smooth Pattern Transformation Manifolds
- Structural Intervention Distance (SID) for Evaluating Causal Graphs
Cited by in corpus (56)
- Distinguishing cause from effect using observational data: methods and benchmarks
- Causal Discovery with Continuous Additive Noise Models
- A Survey on Causal Discovery: Theory and Practice
- Causal Discovery with Reinforcement Learning
- High-dimensional learning of linear causal networks via inverse covariance estimation
- Foundations of Structural Causal Models with Cycles and Latent Variables
- A Graph Autoencoder Approach to Causal Structure Learning
- Learning Causal Semantic Representation for Out-of-Distribution Prediction
- Concave Penalized Estimation of Sparse Gaussian Bayesian Networks
- Causality in cognitive neuroscience: concepts, challenges, and distributional robustness
- Learning Directed Acyclic Graphs with Penalized Neighbourhood Regression
- Causal Structure Learning: a Combinatorial Perspective
- gCastle: A Python Toolbox for Causal Discovery
- Structural Agnostic Modeling: Adversarial Learning of Causal Graphs
- Score-based Causal Learning in Additive Noise Models
- Discovery of causal paths in cardiorespiratory parameters: a time-independent approach in elite athletes
- Consistency of Causal Inference under the Additive Noise Model
- Learning Sparse Nonparametric DAGs
- Distributed Learning of Generalized Linear Causal Networks
- Differentiable Causal Discovery from Interventional Data
- Nonlinear Causal Discovery with Confounders
- Computably Continuous Reinforcement-Learning Objectives are PAC-learnable
- Gradient-Based Neural DAG Learning
- Neural Additive Vector Autoregression Models for Causal Discovery in Time Series
- Treatment Learning Causal Transformer for Noisy Image Classification
- Interactive and Intelligent Root Cause Analysis in Manufacturing with Causal Bayesian Networks and Knowledge Graphs
- Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy To Game
- Model selection and local geometry
- Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization
- A review of Gaussian Markov models for conditional independence
- Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
- Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data
- REX: Causal discovery based on machine learning and explainability techniques
- Ordering-Based Causal Discovery with Reinforcement Learning
- Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery
- On the Convergence of Continuous Constrained Optimization for Structure Learning
- The Evolving Causal Structure of Equity Risk Factors
- Active Invariant Causal Prediction: Experiment Selection through Stability
- Marginal integration for nonparametric causal inference
- A polynomial-time algorithm for learning nonparametric causal graphs
- Latent Instrumental Variables as Priors in Causal Inference based on Independence of Cause and Mechanism
- Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families
- Distance Metrics for Measuring Joint Dependence with Application to Causal Inference
- Variance Minimization in the Wasserstein Space for Invariant Causal Prediction
- Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning
- A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs
- Supervised Whole DAG Causal Discovery
- Fast Causal Discovery by Approximate Kernel-based Generalized Score Functions with Linear Computational Complexity
- Counterfactual Prediction Under Selective Confounding
- Conditionally-additive-noise Models for Structure Learning
- Identifiability of Gaussian Structural Equation Models with Homogeneous and Heterogeneous Error Variances
- Causal Effect Identification in Acyclic Directed Mixed Graphs and Gated Models
- Discovery of Causal Additive Models in the Presence of Unobserved Variables
- KL-BSS: Rethinking optimality for neighbourhood selection in structural equation models
- From graphs to DAGs: a low-complexity model and a scalable algorithm
- Evaluation of Causal Structure Learning Algorithms via Risk Estimation