Neural Information Squeezer for Causal Emergence

Abstract

The classic studies of causal emergence have revealed that in some Markovian dynamical systems, far stronger causal connections can be found on the higher-level descriptions than the lower-level of the same systems if we coarse-grain the system states in an appropriate way. However, identifying this emergent causality from the data is still a hard problem that has not been solved because the correct coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-state dynamics, as well as identify causal emergence directly from the time series data. By decomposing a coarse-graining operation into two processes: information conversion and information dropping out, we can not only exactly control the width of the information channel, but also can derive some important properties analytically including the exact expression of the effective information of a macro-dynamics. We also show how our framework can extract the dynamics on different levels and identify causal emergence from the data on several exampled systems.

33 pages, 9 figures

References in corpus (2)

• Statistical physics through the lens of real-space mutual information
• Flickering emergences: The question of locality in information-theoretic approaches to emergence

Cited by in corpus (4)

• Expectation-Maximizing Network Reconstruction and MostApplicable Network Types Based on Binary Time Series Data
• Finding emergence in data by maximizing effective information
• An Exact Theory of Causal Emergence for Linear Stochastic Iteration Systems
• SVD-based Causal Emergence for Gaussian Iterative Systems