Fast Server Learning Rate Tuning for Coded Federated Dropout.
Giacomo VerardoDaniel BarreiraMarco ChiesaDejan KosticGerald Q. Maguire Jr.Published in: FL@IJCAI (2022)
Keyphrases
- learning rate
- learning algorithm
- convergence rate
- error function
- rapid convergence
- client server
- convergence speed
- hidden layer
- adaptive learning rate
- digital libraries
- multilayer neural networks
- machine learning
- convergence theorem
- weight vector
- activation function
- training algorithm
- accessing data
- data sources
- bp neural network algorithm
- step size
- particle swarm optimization pso
- multi class
- natural gradient
- feature selection
- neural network
- delta bar delta