The Number of Steps Needed for Nonconvex Optimization of a Deep Learning Optimizer is a Rational Function of Batch Size

26 August 2021

Papers citing "The Number of Steps Needed for Nonconvex Optimization of a Deep Learning Optimizer is a Rational Function of Batch Size"

1 / 1 papers shown

Title
Read the Signs: Towards Invariance to Gradient Descent's Hyperparameter Initialization Davood Wadi M. Fredette S. Sénécal ODL AI4CE 8 0 0 24 Jan 2023