Causation Entropy Identifies Indirect Influences, Dominance of Neighbors and Anticipatory Couplings

Abstract

Inference of causality is central in nonlinear time series analysis and science in general. A popular approach to infer causality between two processes is to measure the information flow between them in terms of transfer entropy. Using dynamics of coupled oscillator networks, we show that although transfer entropy can successfully detect information flow in two processes, it often results in erroneous identification of network connections under the presence of indirect interactions, dominance of neighbors, or anticipatory couplings. Such effects are found to be profound for time-dependent networks. To overcome these limitations, we develop a measure called causation entropy and show that its application can lead to reliable identification of true couplings.

References in corpus (11)

• Measuring Information Transfer
• Estimating Mutual Information
• Synchronization in complex networks
• Chimera States for Coupled Oscillators
• Sufficient Conditions for Fast Switching Synchronization in Time Varying Network Topologies
• Master Stability Functions for Coupled Near-Identical Dynamical Systems
• Adaptive synchronization of dynamics on evolving complex networks
• Robustness of Optimal Synchronization in Real Networks
• Validity of threshold-crossing analysis of symbolic dynamics from chaotic time series
• Spontaneous synchronization of coupled oscillator systems with frequency adaptation
• Constructing Generalized Synchronization Manifolds by Manifold Equation

Cited by in corpus (38)

• Causal Network Inference by Optimal Causation Entropy
• Normalizing the causality between time series
• Information Flows? A Critique of Transfer Entropies
• Multivariate Dependence Beyond Shannon Information
• Computational Mechanics of Input-Output Processes: Structured transformations and the $\epsilon$-transducer
• How Entropic Regression Beats the Outliers Problem in Nonlinear System Identification
• Inference of Causal Information Flow in Collective Animal Behavior
• Editorial Comment on the Special Issue of "Information in Dynamical Systems and Complex Systems"
• Identifying Coupling Structure in Complex Systems through the Optimal Causation Entropy Principle
• Optimal model-free prediction from multivariate time series
• Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links
• Anatomy of Leadership in Collective Behaviour
• Information Processing by Networks of Quantum Decision Makers
• Causation entropy from symbolic representations of dynamical systems
• Reconstructing directed and weighted topologies of phase-locked oscillator networks
• Quantum Liang Information Flow as Causation Quantifier
• Complex contagion features without social reinforcement in a model of social information flow
• Causal Inference for Time series Analysis: Problems, Methods and Evaluation
• Shortcomings of transfer entropy and partial transfer entropy: Extending them to escape the curse of dimensionality
• Information flow estimation: a study of news on Twitter
• Information theoretical noninvasive damage detection in bridge structures
• CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
• Open or Closed? Information Flow Decided by Transfer Operators and Forecastability Quality Metric
• An information-theoretic approach to infer the underlying interaction domain among elements from finite length trajectories in a noisy environment
• The quoter model: a paradigmatic model of the social flow of written information
• Granger Causality Based Hierarchical Time Series Clustering for State Estimation
• Can Transfer Entropy Infer Information Flow in Neuronal Circuits for Cognitive Processing?
• Assessing transfer entropy from biochemical data
• On Geometry of Information Flow for Causal Inference
• A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition
• Two-Sample Testing for Event Impacts in Time Series
• Ambiguity Rate of Hidden Markov Processes
• The Design of Global Correlation Quantifiers and Continuous Notions of Statistical Sufficiency
• The Essential Synchronization Backbone Problem
• Directional coupling detection through cross-distance vectors
• Entropic Regression DMD (ERDMD) Discovers Informative Sparse and Nonuniformly Time Delayed Models
• An axiomatic measure of one-way quantum information
• Assimilative Causal Inference