Linear Non Gaussian Acyclic Model

Linear Non-Gaussian Acyclic Models (LiNGAMs) aim to infer causal relationships from observational data by leveraging the assumption that causal influences are linear and noise is non-Gaussian. Current research focuses on extending LiNGAMs to handle latent confounders and high-dimensional data, employing techniques like independent component analysis (ICA), shortest path problem formulations, and functional data analysis to improve identifiability and estimation accuracy. These advancements are significant for causal discovery in various fields, enabling more robust inference of causal structures from complex datasets where traditional methods struggle. The development of efficient algorithms and theoretical guarantees for LiNGAMs under various conditions is a key driver of ongoing research.

Papers

October 30, 2024

QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Mohammad Shahverdikondori, Ehsan Mokhtarian, Negar Kiyavash
Causal Discovery Causal Graph Causal Ordering Linear Non Gaussian Acyclic Model

August 9, 2024

Causal Discovery of Linear Non-Gaussian Causal Models with Unobserved Confounding
Daniela Schkoda, Elina Robeva, Mathias Drton
Causal Discovery Latent Variable Causal Structure Independent Component Analysis Structural Equation Latent Confounding Unmeasured Confounding Linear Non Gaussian Acyclic Model

June 4, 2024

Causal Effect Identification in LiNGAM Models with Latent Confounders
Daniele Tramontano, Yaroslav Kivva, Saber Salehkaleybar, Mathias Drton, Negar Kiyavash
Causal Graph Causal Effect Latent Variable Latent Confounders Causal Effect Identification Parameter Identifiability Linear Non Gaussian Acyclic Model

April 18, 2024

Redefining the Shortest Path Problem Formulation of the Linear Non-Gaussian Acyclic Model: Pairwise Likelihood Ratios, Prior Knowledge, and Path Enumeration
Hans Jarett J. Ong, Brian Godwin S. Lim
Causal Discovery Causal Graph Prior Knowledge Shortest Path Pairwise Learning Causal Discovery Algorithm Linear Non Gaussian Acyclic Model Garden Path Sentence

April 10, 2024

Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata
Jinghong Chen, Weizhe Lin, Jingbiao Mei, Bill Byrne
Language Generation Neural Machine Translation Constrained Decoding Schema Guided Dialogue Weighted Finite Dag DLT Linear Non Gaussian Acyclic Model

January 17, 2024

Functional Linear Non-Gaussian Acyclic Model for Causal Discovery
Tian-Le Yang, Kuang-Yao Lee, Kun Zhang, Joe Suzuki
Causal Discovery Brain Connectivity Linear Non Gaussian Acyclic Model

October 16, 2023

Structural transfer learning of non-Gaussian DAG
Mingyang Ren, Xin He, Junhui Wang
Brain Network Directed Acyclic Graph Linear Non Gaussian Acyclic Model Structure to Structure

August 13, 2023

Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables
Feng Xie, Biwei Huang, Zhengming Chen, Ruichu Cai, Clark Glymour, Zhi Geng, Kun Zhang
Latent Variable Causal Structure Latent Causal Causal Ordering Dependent Noise Linear Non Gaussian Acyclic Model

November 24, 2022

Estimation of a Causal Directed Acyclic Graph Process using Non-Gaussianity
Aref Einizade, Sepideh Hajipour Sardouie
Estimation Task Causal Graph Directed Acyclic Graph Non Gaussianity Linear Non Gaussian Acyclic Model

August 13, 2022

Learning Linear Non-Gaussian Polytree Models
Daniele Tramontano, Anthea Monod, Mathias Drton
Graph Drawing Linear Non Gaussian Acyclic Model Causal Graph Discovery