Stat 928: Statistical Learning Theory Lecture: 24 Growth Functions and the VC dimension Instructor: Sham Kakade

Source URL: stat.wharton.upenn.edu

Hitting Set for Hypergraphs of Low VC-Dimension Karl Bringmann1 , László Kozma2 , Shay Moran3 , and N. S. Narayanaswamy4 1 Institut für Theoretische Informatik, ETH Zürich, Zürich, Switzerland

Source URL: drops.dagstuhl.de

Quantifying Generalization in Linearly Weighted Neural Networks (Short title: Quantifying Generalization) Martin Anthony1 and Sean B. Holden2 Abstract

Source URL: www.maths.lse.ac.uk

• Machine learning
• Learning
• Artificial intelligence
• Computational learning theory
• Computational statistics
• Statistical classification
• Computational neuroscience
• VC dimension
• Artificial neural network
• Probably approximately correct learning
• Probability distribution
• Uniform convergence

A Sufficient Condition for Polynomial Distribution-Dependent Learnability Martin Anthony Department of Mathematics London School of Economics Houghton Street

Source URL: www.maths.lse.ac.uk

• Computational learning theory
• Machine learning
• Learning
• Theoretical computer science
• Cognition
• Probably approximately correct learning
• Sample complexity
• VC dimension
• Mode
• Occam learning
• Error Tolerance

Sampling-based Data Mining Algorithms: Modern Techniques and Case Studies Matteo Riondato Brown University, Providence, RI 02912, USA Abstract. Sampling a dataset for faster analysis and looking at it

Source URL: matteo.rionda.to

• Mathematics
• Graph theory
• Network theory
• Theoretical computer science
• Computational learning theory
• Dimension
• Statistical classification
• VC dimension
• Centrality
• Sampling
• Statistics
• Mode

Journal of Machine Learning Research X (201X) X-XX Submitted 10/13; Published X/XX The VC-Dimension of SQL Queries and Selectivity Estimation Through Sampling

Source URL: matteo.rionda.to

• Data management
• Data
• Computing
• Database management systems
• SQL
• Query optimization
• Data warehousing
• VC dimension
• Join
• Dimension
• Monotonic query

REVlEW The Vapnik-Chervonenkis Dimension: Information versus Complexity in Learning Yaser S. Abu-Mostafa California Institute of Terhnohgy, Pasadcna, CAUSA

Source URL: authors.library.caltech.edu

• Computational learning theory
• Machine learning
• Learning
• Mathematics
• Cognition
• Statistical classification
• Empirical process
• VC dimension
• Probability distribution
• Artificial neural network
• NIP
• Uniform convergence

Mathematical Modelling of Generalization Martin Anthony Department of Mathematics, London School of Economics Houghton Street, London WC2A 2AE, UK www.maths.lse.ac.uk/Personal/martin

Source URL: www.maths.lse.ac.uk

• Machine learning
• Statistical classification
• Computational learning theory
• Decision theory
• Rademacher complexity
• Stability
• VC dimension
• Support vector machine
• Sample complexity
• Generalization error
• VapnikChervonenkis theory

Journal of Machine Learning Research–217 Submitted 8/03; Published 2/04 Generalization Error Bounds for Threshold Decision Lists Martin Anthony

Source URL: www.maths.lse.ac.uk

• Artificial neural networks
• Decision trees
• Generalization error
• Perceptron
• Decision tree model
• Artificial neuron
• Statistical classification
• VC dimension

Probabilistic ‘Generalization’ of Functions and Dimension-based Uniform Convergence Results Martin Anthony Department of Mathematics London School of Economics and Political Science

Source URL: www.maths.lse.ac.uk

• Computational learning theory
• Machine learning
• Probably approximately correct learning
• Uniform convergence
• VC dimension
• Probability distribution
• Stability
• Generalization error