INFORMATION BOTTLENECKS, CAUSAL STATES, AND STATISTICAL RELEVANCE BASES: HOW TO REPRESENT RELEVANT INFORMATION IN MEMORYLESS TRANSDUCTION

DOI10.1142/S0219525902000481zbMath1029.94031MaRDI QIDQ4425279

James P. Crutchfield, Cosma Rohilla Shalizi

Publication date: 24 September 2003

Published in: Advances in Complex Systems (Search for Journal in Brave)

zbMATH Keywords

causal stateoptimal modelsstatistical relevanceinformation-bottleneck methodmemoryless transduction

Mathematics Subject Classification ID

Communication, information (94A99)

Related Items (4)

Predictive rate-distortion for infinite-order Markov processes ⋮ Computational mechanics of input-output processes: structured transformations and the \(\epsilon\)-transducer ⋮ THE INFORMATION BOTTLENECK METHOD FOR OPTIMAL PREDICTION OF MULTILEVEL AGENT-BASED SYSTEMS ⋮ Optimal causal inference: Estimating stored information and approximating causal architecture

Cites Work

• A Mathematical Theory of Communication
• Computational mechanics: pattern and prediction, structure and simplicity.

This page was built for publication: INFORMATION BOTTLENECKS, CAUSAL STATES, AND STATISTICAL RELEVANCE BASES: HOW TO REPRESENT RELEVANT INFORMATION IN MEMORYLESS TRANSDUCTION