Dec 13, 2023 · We propose COTA, the first method to learn abstraction maps from observational and interventional data without assuming complete knowledge of the underlying ...
scholar.google.com › citations
In this section we introduce basic definitions from the field of causality, causal abstractions, and optimal transport. We use the following standard notation ...
May 17, 2024 · Micro/low-level model: Focuses on cellular processes within organs; provides insights into the intricate mechanisms that govern cellular.
Dec 14, 2023 · The COTA framework pushes the boundaries of causal abstraction and representation learning but also of Optimal Transport since constrained multi ...
Dec 14, 2023 · Causal Optimal Transport of Abstractions. Causal abstraction (CA) theory establishes formal criteria for relating multiple structural causal ...
Causal Abstraction: Code, notebooks and resources on the problem of abstraction of structural causal models.
Abstract. An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution.
My current research interests focus on the study of structural causal models and causal abstraction ... Causal Optimal Transport of Abstractions, Published in ...
Aug 27, 2024 · In this paper, we focus on the problem of learning abstractions. We start by defining the learning problem formally in terms of the optimization ...
Jun 1, 2024 · In simu- lated settings, we show the effectiveness of learn- ing causal abstractions from data and the potential of our method in improving ...