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.

arXiv comment33 pages, 9 figures

References in corpus (14)

• Neural Granger Causality
• Graph networks as learnable physics engines for inference and control
• Mutual Information, Neural Networks and the Renormalization Group
• Model-free inference of direct network interactions from nonlinear collective dynamics
• Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data
• Neural Network Renormalization Group
• When the map is better than the territory
• A General Deep Learning Framework for Network Reconstruction and Dynamics Learning
• Machine Learning Holographic Mapping by Neural Network Renormalization Group
• Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators
• Statistical physics through the lens of real-space mutual information
• Flickering emergences: The question of locality in information-theoretic approaches to emergence
• RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior
• Causal Geometry

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