MLITLGOct 5, 2020

Is Information Theory Inherently a Theory of Causation?

arXiv:2010.01932v41 citations
Originality Incremental advance
AI Analysis

This work addresses causal inference for researchers in statistics and machine learning, presenting a novel but incremental approach.

The paper tackles the problem of causal skeleton discovery by proposing a tensor-based method from information theory, which reduces data dimensionality and determines causal structures using pairwise tensors for three-variable systems.

Information theory gives rise to a novel method for causal skeleton discovery by expressing associations between variables as tensors. This tensor-based approach reduces the dimensionality of the data needed to test for conditional independence, e.g., for systems comprising three variables, the causal skeleton can be determined using pair-wise determined tensors. To arrive at this result, an additional information measure, path information, is proposed.

Foundations

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

Your Notes