Optimization / Training

'Optimization / Training' Outline (1)
CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms (1)
AutoAugment: Learning Augmentation Policies from Data (1)
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (1)
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models (1)
Neural Architecture Search with Reinforcement Learning (1)
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (1)