Preconditioned Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression.
Yingzhen YangPublished in: CoRR (2024)
Keyphrases
- nonparametric regression
- neural network
- iterative methods
- pattern recognition
- learning rules
- pointwise
- cost function
- artificial neural networks
- neural nets
- objective function
- high quality
- fuzzy systems
- fuzzy logic
- multilayer perceptron
- recurrent neural networks
- training process
- fuzzy neural network
- back propagation
- feed forward
- neural network model
- computationally expensive
- self organizing maps
- neural model
- least squares