AIDec 23, 2022

Continual Causal Abstractions

arXiv:2212.12575v21 citationsh-index: 6
Originality Synthesis-oriented
AI Analysis

This is an incremental proposal for future research in causal inference, with no specific problem or audience defined.

The paper proposes continually updated causal abstractions as a research direction, aiming to revise causal abstraction levels to be consistent with historical data and more effective for tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes