artifact
active
artifact:yuan-2023-emergence-and-causality-in-complex-systems-a-surveyYuan 2023 Emergence and Causality in Complex Systems: A Survey
This review paper surveys quantitative theories of causal emergence and their connections to machine learning.
Neighborhood — ranked by edge-count
Thinkers (33)
thinker
- Michael Levinmentions
- Anil Sethmentions
- Giulio TononimentionsDeveloper of integrated information theory; provides formal tools for measuring integration and consciousness in systems.
- Judea PearlmentionsDeveloped causal graph models and the do-operator, foundational to modern causal inference.
- Erik HoelmentionsAuthor of 'The Overfitted Brain'; Johnson references Hoel's framework of energy, information, and uncertainty as equivalent conserved quantities.
- Jiang Zhangauthored
- Mingzhe Yangauthored
- Aobo Lyuauthored
- Bing Yuanauthored
- James P. CrutchfieldmentionsCo-author studying perception and emergence in populations of interacting agents; bridges perception and collective dynamics.
- Jiayun Wuauthored
- Larissa AlbantakismentionsCo-author with Hoel and Tononi on quantitative causal emergence.
- Muyun Mouauthored
- Peng Cuiauthored
- Zhipeng Wangauthored
- Fernando E. RosasmentionsDeveloped the φID framework for causal emergence and downward causation.
- Joe DewhurstmentionsCritiqued Hoel's causal emergence as epistemological rather than ontological.
- Kaiwei Liuauthored
- Mark A. BedaumentionsFormulated weak emergence theory and classifications (nominal, weak, strong).
- Paul L. WilliamsmentionsCo-developed the partial information decomposition (PID) framework.
- Pavel ChvykovmentionsCo-developed causal geometry with Erik Hoel.
- Randall D. BeermentionsCo-developed PID with Williams.
- Sergey YurchenkomentionsProposed causal equivalence principle distinguishing cause and reason.
- Anand SwainmentionsApplied EI to ant colony task allocation.
+9 more
Frameworks (10)
framework
- Hoel's Causal Emergence TheorymentionsQuantitative emergence theory based on Markov dynamics and effective information (EI).
- Machine learning framework for causal emergence identification via encoder-dynamics learner-decoder architecture.
- Extension of NIS that directly maximizes effective information using probability reweighting.
- A mathematical framework for decomposing information flow into causal constituents, used here to quantify causal emergence from latent dynamics.
- Rosas's Causal Emergence via φIDmentionsQuantitative emergence framework using partial information decomposition and integrated information decomposition.
- Causal GeometrymentionsChvykov and Hoel's geometric extension of causal emergence to continuous systems using Fisher information.
- Williams and Beer's decomposition of joint mutual information into unique, redundant, and synergistic components.
- Computational MechanicsmentionsCrutchfield's framework inferring minimal causal models from stochastic processes; causal states and transition matrices.
- G-EmergencementionsSeth's quantitative emergence measure based on Granger causality.
- Schölkopf et al.'s framework combining representation learning with causal inference.
Concepts (1)
concept
- Effective Information (EI)mentionsCore measure of causal effect in Hoel's theory; mutual information between uniform input and output distributions.