1 citations · 1 across the 1 of their papers we have counts for
2 papers
stat.ML2021★ 1 cited
GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks
Younghwan Chae, Daniel N. Wilke, Dominic Kafka
Mini-batch sub-sampling (MBSS) is favored in deep neural network training to reduce the computational cost. Still, it introduces an inherent sampling error, making the selection of…
stat.ML2019
Empirical study towards understanding line search approximations for training neural networks
Younghwan Chae, Daniel N. Wilke
Choosing appropriate step sizes is critical for reducing the computational cost of training large-scale neural network models. Mini-batch sub-sampling (MBSS) is often employed for…