Fast Parallel Estimation of High Dimensional Information Theoretical Quantities with Low Dimensional Random Projection Ensembles

DOI10.1007/978-3-642-00599-2_19zbMath1301.94041MaRDI QIDQ3614946

András C. Lőrincz, Zoltán Szabó

Publication date: 17 March 2009

Published in: Independent Component Analysis and Signal Separation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-642-00599-2_19

zbMATH Keywords

random projection; independent subspace analysis; pairwise distances; information theoretical estimations

Mathematics Subject Classification ID

94A15: Information theory (general)

Cites Work

• A Mathematical Theory of Communication
• The transform likelihood ratio method for rare event simulation with heavy tails
• Blind separation of sources. I: An adaptive algorithm based on neuromimetic architecture
• Uniqueness of complex and multidimensional independent component analysis
• A simple proof of the restricted isometry property for random matrices
• Sample estimate of the entropy of a random vector
• An algorithmic theory of learning: Robust concepts and random projection
• An optimal algorithm for approximate nearest neighbor searching fixed dimensions
• Extensions of Lipschitz mappings into a Hilbert space
• On variants of the Johnson–Lindenstrauss lemma
• Independent Process Analysis Without a Priori Dimensional Information
• 10.1162/jmlr.2003.4.7-8.1205
• 10.1162/jmlr.2003.4.7-8.1271
• Independent Component Analysis and Blind Signal Separation
• Unnamed Item
• Unnamed Item