Normalized Direction-preserving Adam

13 September 2017

Papers citing "Normalized Direction-preserving Adam"

5 / 5 papers shown

Title
DEAM: Adaptive Momentum with Discriminative Weight for Stochastic Optimization Jiyang Bai Yuxiang Ren Jiawei Zhang ODL 18 1 0 25 Jul 2019
Removing the Feature Correlation Effect of Multiplicative Noise Zijun Zhang Yining Zhang Zongpeng Li 11 8 0 19 Sep 2018
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks Jinghui Chen Dongruo Zhou Yiqi Tang Ziyan Yang Yuan Cao Quanquan Gu ODL 19 192 0 18 Jun 2018
Decoupled Weight Decay Regularization I. Loshchilov Frank Hutter OffRL 30 2,078 0 14 Nov 2017
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 281 2,888 0 15 Sep 2016