14 citations · 31 across the 15 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 14 cited
Towards Understanding the Importance of Noise in Training Neural Networks
Mo Zhou, Tianyi Liu, Yan Li +3
Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largel…
stat.ML2019
Towards Better Generalization: BP-SVRG in Training Deep Neural Networks
Hao Jin, Dachao Lin, Zhihua Zhang
Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient…