Critical Bach Size Minimizes Stochastic First-Order Oracle Complexity of Deep Learning Optimizer using Hyperparameters Close to One

21 August 2022

Papers citing "Critical Bach Size Minimizes Stochastic First-Order Oracle Complexity of Deep Learning Optimizer using Hyperparameters Close to One"

2 / 2 papers shown

Title
Relationship between Batch Size and Number of Steps Needed for Nonconvex Optimization of Stochastic Gradient Descent using Armijo Line Search Yuki Tsukada Hideaki Iiduka 18 0 0 25 Jul 2023
Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update Rule Naoki Sato Hideaki Iiduka EGVM 18 4 0 28 Jan 2022