Saved in:
Bibliographic Details
Main Authors: Wei, Mian, Jha, Somesh, Page, David
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.18903
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913959634796544
author Wei, Mian
Jha, Somesh
Page, David
author_facet Wei, Mian
Jha, Somesh
Page, David
contents The discovery of causal relationships is a foundational problem in artificial intelligence, statistics, epidemiology, economics, and beyond. While elegant theories exist for accurate causal discovery given infinite data, real-world applications are inherently resource-constrained. Effective methods for inferring causal relationships from observational data must perform well under finite data and time constraints, where "performing well" implies achieving high, though not perfect accuracy. In his seminal paper A Theory of the Learnable, Valiant highlighted the importance of resource constraints in supervised machine learning, introducing the concept of Probably Approximately Correct (PAC) learning as an alternative to exact learning. Inspired by Valiant's work, we propose the Probably Approximately Correct Causal (PACC) Discovery framework, which extends PAC learning principles to the causal field. This framework emphasizes both computational and sample efficiency for established causal methods such as propensity score techniques and instrumental variable approaches. Furthermore, we show that it can also provide theoretical guarantees for other widely used methods, such as the Self-Controlled Case Series (SCCS) method, which had previously lacked such guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18903
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probably Approximately Correct Causal Discovery
Wei, Mian
Jha, Somesh
Page, David
Machine Learning
The discovery of causal relationships is a foundational problem in artificial intelligence, statistics, epidemiology, economics, and beyond. While elegant theories exist for accurate causal discovery given infinite data, real-world applications are inherently resource-constrained. Effective methods for inferring causal relationships from observational data must perform well under finite data and time constraints, where "performing well" implies achieving high, though not perfect accuracy. In his seminal paper A Theory of the Learnable, Valiant highlighted the importance of resource constraints in supervised machine learning, introducing the concept of Probably Approximately Correct (PAC) learning as an alternative to exact learning. Inspired by Valiant's work, we propose the Probably Approximately Correct Causal (PACC) Discovery framework, which extends PAC learning principles to the causal field. This framework emphasizes both computational and sample efficiency for established causal methods such as propensity score techniques and instrumental variable approaches. Furthermore, we show that it can also provide theoretical guarantees for other widely used methods, such as the Self-Controlled Case Series (SCCS) method, which had previously lacked such guarantees.
title Probably Approximately Correct Causal Discovery
topic Machine Learning
url https://arxiv.org/abs/2507.18903