Exponentially Growing Learning Rate? Implications of Scale Invariance induced by Batch Normalization

Yesterday I read this intriguing paper about the midboggling fact that it is possible to use exponentially growing learning rate schedule when training neural networks with batch normalization:Zhiyuan Li and Sanjeev Arora (2019) An Exponential Learning Rate Schedule for Deep LearningThe paper provides both theoretical insights as well as empirical demonstration of this remarcable property.

Read Full Story