Convexifying Sparse Interpolation with Infinitely Wide Neural Networks: An Atomic Norm Approach.
Akshay KumarJarvis D. HauptPublished in: CoRR (2020)
Keyphrases
- neural network
- sparse sampling
- low rank matrices
- regularized least squares
- finite number
- wide range
- neural network model
- genetic algorithm
- robust principal component analysis
- mixed norm
- pattern recognition
- artificial neural networks
- fuzzy logic
- back propagation
- self organizing maps
- linear interpolation
- compressed sensing
- sparse data
- sparse representation
- interpolation method
- recurrent neural networks
- multilayer perceptron
- sparse learning
- feed forward
- training process
- denoising
- multi layer perceptron
- fuzzy systems
- multi layer
- interpolation methods
- sparse matrix
- norm regularization
- high dimensional
- objective function