Yasutoshi Ida, Yasuhiro Fujiwara. Improving Generalization Performance of Adaptive Learning Rate by Switching from Block Diagonal Matrix Preconditioning to SGD. In 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19-24, 2020. pages 1-8, IEEE, 2020. [doi]
Abstract is missing.