amsgrad topic

Reproducing the paper "PADAM: Closing The Generalization Gap of Adaptive Gradient Methods In Training Deep Neural Networks" for the ICLR 2019 Reproducibility Challenge

yashkant

Custom Optimizer in TensorFlow(定义你自己的Tensorflow Optimizer)

luochuwei

Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay

JRC1995

[Python] [arXiv/cs] Paper "An Overview of Gradient Descent Optimization Algorithms" by Sebastian Ruder

harshraj11584