-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields.
Kefan DongTengyu MaPublished in: CoRR (2023)
Keyphrases
- nonlinear functions
- sample complexity
- random fields
- upper bound
- vc dimension
- lower bound
- rbf network
- input output
- neural network
- markov random field
- maximum entropy
- learning algorithm
- theoretical analysis
- learning problems
- generalization error
- non stationary
- nonlinear systems
- parameter estimation
- special case
- basis functions
- conditional random fields
- worst case
- active learning
- supervised learning
- training examples
- sample size
- probabilistic model
- radial basis function
- rbf neural network
- training data
- objective function
- higher order
- learning rate
- learning tasks
- semi supervised learning
- model selection