Exploring predictive states via Cantor embeddings and Wasserstein distance

DOI10.1063/5.0102603MaRDI QIDQ6571499FDOQ6571499

Authors: Samuel P. Loomis, James P. Crutchfield 

Publication date: 12 July 2024

Published in: Chaos (Search for Journal in Brave)

Mathematics Subject Classification ID

Dynamical systems and ergodic theory (37-XX) Ordinary differential equations (34-XX)

Cites Work

• Modern multidimensional scaling. Theory and applications.
• Title not available (Why is that?)
• Hilbert space embeddings and metrics on probability measures
• Comparing distributions
• The Future of Data Analysis
• Title not available (Why is that?)
• Title not available (Why is that?)
• Regularities unseen, randomness observed: Levels of entropy convergence
• Computational mechanics: pattern and prediction, structure and simplicity.
• The calculi of emergence: Computation, dynamics and induction
• Optimal causal inference: estimating stored information and approximating causal architecture
• Statistical signatures of structural organization: the case of long memory in renewal processes
• Links between multiplicity automata, observable operator models and predictive state representations -- a unified learning framework
• Discovering causal structure with reproducing-kernel Hilbert space \(\epsilon\)-machines

This page was built for publication: Exploring predictive states via Cantor embeddings and Wasserstein distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6571499)