Alert button
Picture for Mathias Drton

Mathias Drton

Alert button

$\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery

Jun 19, 2023
Konstantin Göbler, Tobias Windisch, Tim Pychynski, Steffen Sonntag, Martin Roth, Mathias Drton

Figure 1 for $\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery
Figure 2 for $\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery
Figure 3 for $\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery
Figure 4 for $\texttt{causalAssembly}$: Generating Realistic Production Data for Benchmarking Causal Discovery

Algorithms for causal discovery have recently undergone rapid advances and increasingly draw on flexible nonparametric methods to process complex data. With these advances comes a need for adequate empirical validation of the causal relationships learned by different algorithms. However, for most real data sources true causal relations remain unknown. This issue is further compounded by privacy concerns surrounding the release of suitable high-quality data. To help address these challenges, we gather a complex dataset comprising measurements from an assembly line in a manufacturing context. This line consists of numerous physical processes for which we are able to provide ground truth causal relationships on the basis of a detailed study of the underlying physics. We use the assembly line data and associated ground truth information to build a system for generation of semisynthetic manufacturing data that supports benchmarking of causal discovery methods. To accomplish this, we employ distributional random forests in order to flexibly estimate and represent conditional distributions that may be combined into joint distributions that strictly adhere to a causal model over the observed variables. The estimated conditionals and tools for data generation are made available in our Python library $\texttt{causalAssembly}$. Using the library, we showcase how to benchmark several well-known causal discovery algorithms.

Viaarxiv icon

Rank-Based Causal Discovery for Post-Nonlinear Models

Feb 23, 2023
Grigor Keropyan, David Strieder, Mathias Drton

Figure 1 for Rank-Based Causal Discovery for Post-Nonlinear Models
Figure 2 for Rank-Based Causal Discovery for Post-Nonlinear Models
Figure 3 for Rank-Based Causal Discovery for Post-Nonlinear Models
Figure 4 for Rank-Based Causal Discovery for Post-Nonlinear Models

Learning causal relationships from empirical observations is a central task in scientific research. A common method is to employ structural causal models that postulate noisy functional relations among a set of interacting variables. To ensure unique identifiability of causal directions, researchers consider restricted subclasses of structural causal models. Post-nonlinear (PNL) causal models constitute one of the most flexible options for such restricted subclasses, containing in particular the popular additive noise models as a further subclass. However, learning PNL models is not well studied beyond the bivariate case. The existing methods learn non-linear functional relations by minimizing residual dependencies and subsequently test independence from residuals to determine causal orientations. However, these methods can be prone to overfitting and, thus, difficult to tune appropriately in practice. As an alternative, we propose a new approach for PNL causal discovery that uses rank-based methods to estimate the functional parameters. This new approach exploits natural invariances of PNL models and disentangles the estimation of the non-linear functions from the independence tests used to find causal orientations. We prove consistency of our method and validate our results in numerical experiments.

* Accepted for the 26th International Conference on Artificial Intelligence and Statistics (AISTATS) 2023 
Viaarxiv icon

Unpaired Multi-Domain Causal Representation Learning

Feb 02, 2023
Nils Sturma, Chandler Squires, Mathias Drton, Caroline Uhler

Figure 1 for Unpaired Multi-Domain Causal Representation Learning
Figure 2 for Unpaired Multi-Domain Causal Representation Learning
Figure 3 for Unpaired Multi-Domain Causal Representation Learning
Figure 4 for Unpaired Multi-Domain Causal Representation Learning

The goal of causal representation learning is to find a representation of data that consists of causally related latent variables. We consider a setup where one has access to data from multiple domains that potentially share a causal representation. Crucially, observations in different domains are assumed to be unpaired, that is, we only observe the marginal distribution in each domain but not their joint distribution. In this paper, we give sufficient conditions for identifiability of the joint distribution and the shared causal graph in a linear setup. Identifiability holds if we can uniquely recover the joint distribution and the shared causal representation from the marginal distributions in each domain. We transform our identifiability results into a practical method to recover the shared latent causal graph. Moreover, we study how multiple domains reduce errors in falsely detecting shared causal variables in the finite data setting.

Viaarxiv icon

High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data

Nov 21, 2022
Konstantin Göbler, Anne Miloschewski, Mathias Drton, Sach Mukherjee

Figure 1 for High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data
Figure 2 for High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data
Figure 3 for High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data
Figure 4 for High-Dimensional Undirected Graphical Models for Arbitrary Mixed Data

Graphical models are an important tool in exploring relationships between variables in complex, multivariate data. Methods for learning such graphical models are well developed in the case where all variables are either continuous or discrete, including in high-dimensions. However, in many applications data span variables of different types (e.g. continuous, count, binary, ordinal, etc.), whose principled joint analysis is nontrivial. Latent Gaussian copula models, in which all variables are modeled as transformations of underlying jointly Gaussian variables, represent a useful approach. Recent advances have shown how the binary-continuous case can be tackled, but the general mixed variable type regime remains challenging. In this work, we make the simple yet useful observation that classical ideas concerning polychoric and polyserial correlations can be leveraged in a latent Gaussian copula framework. Building on this observation we propose flexible and scalable methodology for data with variables of entirely general mixed type. We study the key properties of the approaches theoretically and empirically, via extensive simulations as well an illustrative application to data from the UK Biobank concerning COVID-19 risk factors.

* 17 pages, 2 Figures 
Viaarxiv icon

Learning Linear Non-Gaussian Polytree Models

Aug 13, 2022
Daniele Tramontano, Anthea Monod, Mathias Drton

Figure 1 for Learning Linear Non-Gaussian Polytree Models
Figure 2 for Learning Linear Non-Gaussian Polytree Models
Figure 3 for Learning Linear Non-Gaussian Polytree Models
Figure 4 for Learning Linear Non-Gaussian Polytree Models

In the context of graphical causal discovery, we adapt the versatile framework of linear non-Gaussian acyclic models (LiNGAMs) to propose new algorithms to efficiently learn graphs that are polytrees. Our approach combines the Chow--Liu algorithm, which first learns the undirected tree structure, with novel schemes to orient the edges. The orientation schemes assess algebraic relations among moments of the data-generating distribution and are computationally inexpensive. We establish high-dimensional consistency results for our approach and compare different algorithmic versions in numerical experiments.

Viaarxiv icon

Graphical Representations for Algebraic Constraints of Linear Structural Equations Models

Aug 01, 2022
Thijs van Ommen, Mathias Drton

Figure 1 for Graphical Representations for Algebraic Constraints of Linear Structural Equations Models
Figure 2 for Graphical Representations for Algebraic Constraints of Linear Structural Equations Models
Figure 3 for Graphical Representations for Algebraic Constraints of Linear Structural Equations Models
Figure 4 for Graphical Representations for Algebraic Constraints of Linear Structural Equations Models

The observational characteristics of a linear structural equation model can be effectively described by polynomial constraints on the observed covariance matrix. However, these polynomials can be exponentially large, making them impractical for many purposes. In this paper, we present a graphical notation for many of these polynomial constraints. The expressive power of this notation is investigated both theoretically and empirically.

* To appear in the proceedings of the 11th International Conference on Probabilistic Graphical Models (PGM 2022) 
Viaarxiv icon

Interaction Models and Generalized Score Matching for Compositional Data

Sep 10, 2021
Shiqing Yu, Mathias Drton, Ali Shojaie

Figure 1 for Interaction Models and Generalized Score Matching for Compositional Data
Figure 2 for Interaction Models and Generalized Score Matching for Compositional Data
Figure 3 for Interaction Models and Generalized Score Matching for Compositional Data
Figure 4 for Interaction Models and Generalized Score Matching for Compositional Data

Applications such as the analysis of microbiome data have led to renewed interest in statistical methods for compositional data, i.e., multivariate data in the form of probability vectors that contain relative proportions. In particular, there is considerable interest in modeling interactions among such relative proportions. To this end we propose a class of exponential family models that accommodate general patterns of pairwise interaction while being supported on the probability simplex. Special cases include the family of Dirichlet distributions as well as Aitchison's additive logistic normal distributions. Generally, the distributions we consider have a density that features a difficult to compute normalizing constant. To circumvent this issue, we design effective estimation methods based on generalized versions of score matching. A high-dimensional analysis of our estimation methods shows that the simplex domain is handled as efficiently as previously studied full-dimensional domains.

* 41 pages, 19 figures 
Viaarxiv icon

Definite Non-Ancestral Relations and Structure Learning

May 20, 2021
Wenyu Chen, Mathias Drton, Ali Shojaie

Figure 1 for Definite Non-Ancestral Relations and Structure Learning
Figure 2 for Definite Non-Ancestral Relations and Structure Learning
Figure 3 for Definite Non-Ancestral Relations and Structure Learning
Figure 4 for Definite Non-Ancestral Relations and Structure Learning

In causal graphical models based on directed acyclic graphs (DAGs), directed paths represent causal pathways between the corresponding variables. The variable at the beginning of such a path is referred to as an ancestor of the variable at the end of the path. Ancestral relations between variables play an important role in causal modeling. In existing literature on structure learning, these relations are usually deduced from learned structures and used for orienting edges or formulating constraints of the space of possible DAGs. However, they are usually not posed as immediate target of inference. In this work we investigate the graphical characterization of ancestral relations via CPDAGs and d-separation relations. We propose a framework that can learn definite non-ancestral relations without first learning the skeleton. This frame-work yields structural information that can be used in both score- and constraint-based algorithms to learn causal DAGs more efficiently.

Viaarxiv icon

Generalized Score Matching for General Domains

Sep 24, 2020
Shiqing Yu, Mathias Drton, Ali Shojaie

Figure 1 for Generalized Score Matching for General Domains
Figure 2 for Generalized Score Matching for General Domains
Figure 3 for Generalized Score Matching for General Domains
Figure 4 for Generalized Score Matching for General Domains

Estimation of density functions supported on general domains arises when the data is naturally restricted to a proper subset of the real space. This problem is complicated by typically intractable normalizing constants. Score matching provides a powerful tool for estimating densities with such intractable normalizing constants, but as originally proposed is limited to densities on $\mathbb{R}^m$ and $\mathbb{R}_+^m$. In this paper, we offer a natural generalization of score matching that accommodates densities supported on a very general class of domains. We apply the framework to truncated graphical and pairwise interaction models, and provide theoretical guarantees for the resulting estimators. We also generalize a recently proposed method from bounded to unbounded domains, and empirically demonstrate the advantages of our method.

* 50 pages, 14 figures 
Viaarxiv icon

Structure Learning for Cyclic Linear Causal Models

Jun 10, 2020
Carlos Améndola, Philipp Dettling, Mathias Drton, Federica Onori, Jun Wu

Figure 1 for Structure Learning for Cyclic Linear Causal Models
Figure 2 for Structure Learning for Cyclic Linear Causal Models
Figure 3 for Structure Learning for Cyclic Linear Causal Models
Figure 4 for Structure Learning for Cyclic Linear Causal Models

We consider the problem of structure learning for linear causal models based on observational data. We treat models given by possibly cyclic mixed graphs, which allow for feedback loops and effects of latent confounders. Generalizing related work on bow-free acyclic graphs, we assume that the underlying graph is simple. This entails that any two observed variables can be related through at most one direct causal effect and that (confounding-induced) correlation between error terms in structural equations occurs only in absence of direct causal effects. We show that, despite new subtleties in the cyclic case, the considered simple cyclic models are of expected dimension and that a previously considered criterion for distributional equivalence of bow-free acyclic graphs has an analogue in the cyclic case. Our result on model dimension justifies in particular score-based methods for structure learning of linear Gaussian mixed graph models, which we implement via greedy search.

* 19 pages, 5 figures, 3 tables, to appear in UAI 2020 
Viaarxiv icon