Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wienöbst, Marcel, Henckel, Leonard, Weichwald, Sebastian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918358829498368
author Wienöbst, Marcel
Henckel, Leonard
Weichwald, Sebastian
author_facet Wienöbst, Marcel
Henckel, Leonard
Weichwald, Sebastian
contents We present FLOP (Fast Learning of Order and Parents), a score-based causal discovery algorithm for linear models. It pairs fast parent selection with iterative Cholesky-based score updates, cutting run-times over prior algorithms. This makes it feasible to fully embrace discrete search, enabling iterated local search with principled order initialization to find graphs with scores at or close to the global optimum. The resulting structures are highly accurate across benchmarks, with near-perfect recovery in standard settings. This performance calls for revisiting discrete search over graphs as a reasonable approach to causal discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04970
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning
Wienöbst, Marcel
Henckel, Leonard
Weichwald, Sebastian
Machine Learning
Artificial Intelligence
Methodology
We present FLOP (Fast Learning of Order and Parents), a score-based causal discovery algorithm for linear models. It pairs fast parent selection with iterative Cholesky-based score updates, cutting run-times over prior algorithms. This makes it feasible to fully embrace discrete search, enabling iterated local search with principled order initialization to find graphs with scores at or close to the global optimum. The resulting structures are highly accurate across benchmarks, with near-perfect recovery in standard settings. This performance calls for revisiting discrete search over graphs as a reasonable approach to causal discovery.
title Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning
topic Machine Learning
Artificial Intelligence
Methodology
url https://arxiv.org/abs/2510.04970