SVD-based Causal Emergence for Gaussian Iterative Systems

Abstract

Causal emergence (CE) based on effective information (EI) demonstrates that macro-states can exhibit stronger causal effects than micro-states in dynamics. However, the identification of CE and the maximization of EI both rely on coarse-graining strategies, which is a key challenge. A recently proposed CE framework based on approximate dynamical reversibility, utilizing singular value decomposition (SVD), is independent of coarse-graining. Still, it is limited to transition probability matrices (TPM) in discrete states. To address this, this article proposes a novel CE quantification framework for Gaussian iterative systems (GIS), based on approximate dynamical reversibility derived from the SVD of inverse covariance matrices in forward and backward dynamics. The positive correlation between SVD-based and EI-based CE, along with the equivalence condition, is given analytically. After that, we provide precise coarse-graining strategies directly from singular value spectra and orthogonal matrices. This new framework can be applied to any dynamical system with continuous states and Gaussian noise, such as auto-regressive growth models, Markov-Gaussian systems, and even SIR modeling using neural networks (NN). Numerical simulations on typical cases validate our theory and offer a new approach to studying the CE phenomenon, emphasizing noise and covariance over dynamical functions in both known models and machine learning.

References in corpus (16)

• Measuring Information Transfer
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• A Review of Stochastic Block Models and Extensions for Graph Clustering
• Statistical physics approaches to the complex Earth system
• Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate data
• Stochastic Dynamical Structure (SDS) of Nonequilibrium Processes in the Absence of Detailed Balance. IV: Emerging of Stochastic Dynamical Equalities and Steady State Thermodynamics from Darwinian Dynamics
• When the map is better than the territory
• On Causality in Dynamical Systems
• Mutual Information as a Tool for Identifying Phase Transitions in Dynamical Complex Systems With Limited Data
• Expectation-Maximizing Network Reconstruction and MostApplicable Network Types Based on Binary Time Series Data
• Dynamical independence: discovering emergent macroscopic processes in complex dynamical systems
• Neural Information Squeezer for Causal Emergence
• Finding emergence in data by maximizing effective information
• Causal Geometry
• Unveiling the early stage evolution of local atomic structures in the crystallization process of a metallic glass
• An Exact Theory of Causal Emergence for Linear Stochastic Iteration Systems