vix.ing · top · new · best · stats · spec

Continual Causal Abstractions

2022/12/23 by Matej Zečević, Zečević, Matej, Moritz Willig +5
Computer Science · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2212.12575

openalex publication_date 2022/12/23 · openalex created_date 2023/01/04 · openalex updated_date 2026/07/28

Abstract

This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history of observed data and more effective in solving a given task.

Related