Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well.
Vipul GuptaSantiago Akle SerranoDennis DeCostePublished in: CoRR (2020)
Keyphrases
- training set
- training process
- batch mode
- supervised learning
- stochastic optimization
- parallel processing
- monte carlo
- weight assignment
- training algorithm
- test set
- training examples
- evolutionary algorithm
- neural network
- multistage
- training samples
- parallel implementation
- training phase
- learning automata
- case study
- data sets