On the value of partial information for learning from examples

DOI10.1006/jcom.1997.0459zbMath0894.68063OpenAlexW2125325175MaRDI QIDQ1383444

Joel Ratsaby, Vitaly Maiorov

Publication date: 20 April 1998

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/4ba516f8a1222b2e2d6bdf0d068945b57877e2bf

zbMATH Keywords

PAC model of learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Complexity classes (hierarchies, relations among complexity classes, etc.) (68Q15)

Related Items

Learning with side information: PAC learning bounds ⋮ Nonlinear approximation of functions by sets of finite pseudo-dimension in the probabilistic and average case settings ⋮ Approximation in shift-invariant spaces with deep ReLU neural networks ⋮ Continuous algorithms in \(n\)-term approximation and nonlinear widths ⋮ Approximation by neural networks and learning theory ⋮ Some problems in the theory of ridge functions ⋮ The degree of approximation of sets in euclidean space using sets with bounded Vapnik-Chervonenkis dimension ⋮ Approximation of Sobolev-type classes with quasi-seminorms ⋮ On the orders of nonlinear approximations for classes of functions of given form

Cites Work

• Learning from hints in neural networks
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• On the degree of approximation by manifolds of finite pseudo-dimension
• On best approximation by ridge functions
• Probabilistic and average linear width in \(L_ \infty\)-norm with respect to \(r\)-fold Wiener measure
• Fat-shattering and the learnability of real-valued functions
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
• Scale-sensitive dimensions, uniform convergence, and learnability
• Learning by canonical smooth estimation. I. Simultaneous estimation
• Probability Inequalities for Sums of Bounded Random Variables
• Lower Bounds for Approximation by Nonlinear Manifolds
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convergence of stochastic processes
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item