Learning distributions by their density levels: A paradigm for learning without a teacher

DOI10.1006/jcss.1997.1507zbMath0880.68106OpenAlexW2005530305MaRDI QIDQ1370866

Shai Ben-David, Michael Lindenbaum

Publication date: 7 January 1998

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/cda0324c7f815d53d75149ea97b122f15e5b2f1c

zbMATH Keywords

PAC learningdensity-level learnability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Related Items (5)

Fully adaptive density-based clustering ⋮ LEARNING RATES FOR DENSITY LEVEL DETECTION ⋮ Estimating the Support of a High-Dimensional Distribution ⋮ Support vector machines for default prediction of SMEs based on technology credit ⋮ The computational complexity of densest region detection

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Lower bounds for sampling algorithms for estimating the average
• Learnability with respect to fixed distributions
• A general lower bound on the number of examples needed for learning
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• General bounds on the number of examples needed for learning probabilistic concepts
• On the learnability of discrete distributions
• Probably Approximate Learning of Sets and Functions
• Learnability and the Vapnik-Chervonenkis dimension
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Learning distributions by their density levels: A paradigm for learning without a teacher