Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel.
Colin WeiJason D. LeeQiang LiuTengyu MaPublished in: NeurIPS (2019)
Keyphrases
- neural nets
- kernel machines
- feed forward
- neural network
- backpropagation neural networks
- optimal kernel
- reproducing kernel hilbert space
- counter propagation
- single layer
- back propagation
- optimization problems
- support vector
- stochastic gradient descent
- artificial neural networks
- image processing
- representer theorem
- learning tasks
- kernel ridge regression
- kernel function
- higher order
- information retrieval
- multiple kernel learning
- fuzzy logic
- pairwise
- artificial intelligence
- genetic algorithm