SVD-based Causal Emergence for Gaussian Iterative Systems

Abstract: Causal emergence (CE) based on effective information (EI) shows 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 but is limited to transition probability matrices (TPM) in discrete states. To address this problem, this article proposes a pioneering CE quantification framework for Gaussian iterative systems (GIS), based on approximate dynamical reversibility derived from SVD of covariance matrices in forward and backward dynamics. The positive correlation between SVD-based and EI-based CE, along with the equivalence condition, are given analytically. After that, we can provide precise coarse-graining strategies directly from singular value spectrums 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 by 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.