Almost Linear VC-Dimension Bounds for Piecewise Polynomial Networks.
Peter L. BartlettVitaly MaiorovRon MeirPublished in: Neural Comput. (1998)
Keyphrases
- vc dimension
- vapnik chervonenkis dimension
- piecewise polynomial
- upper bound
- covering numbers
- lower bound
- vapnik chervonenkis
- sample size
- sample complexity
- concept classes
- distribution free
- empirical risk minimization
- inductive inference
- uniform convergence
- worst case
- statistical learning theory
- learning machines
- generalization bounds
- pac learning
- risk bounds
- compression scheme
- euclidean space
- function classes
- concept class
- least squares
- b spline
- computational complexity