A Survey on Causal Discovery: Theory and Practice
read the original abstract
Understanding the laws that govern a phenomenon is the core of scientific progress. This is especially true when the goal is to model the interplay between different aspects in a causal fashion. Indeed, causal inference itself is specifically designed to quantify the underlying relationships that connect a cause to its effect. Causal discovery is a branch of the broader field of causality in which causal graphs are recovered from data (whenever possible), enabling the identification and estimation of causal effects. In this paper, we explore recent advancements in causal discovery in a unified manner, provide a consistent overview of existing algorithms developed under different settings, report useful tools and data, present real-world applications to understand why and how these methods can be fruitfully exploited.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Learning Causal Orderings for In-Context Tabular Prediction
TabOrder learns unsupervised causal variable orderings and enforces them with order-constrained attention for tabular prediction and imputation under distribution shifts.
-
Causal Persuasion
Causal persuasion succeeds with minimal disclosure to establish a link but demands exhaustive disclosure of common causes to rule one out, creating a fundamental asymmetry.
-
Markovianity-Based Conditioning Depth Diagnostics for Hidden Confounding in Observational Datasets
A diagnostic that measures instability of constraint-based causal graphs over increasing conditioning depths to detect hidden confounding or incomplete state in time series observational data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.