ICLR Reproducibility Challenge Report (Padam : Closing The Generalization Gap Of Adaptive Gradient Methods in Training Deep Neural Networks)

Harshal Mittal, Kartikey Pandey, Yash Kant

This work is a part of ICLR Reproducibility Challenge 2019, we try to reproduce the results in the conference submission PADAM: Closing The Generalization Gap of Adaptive Gradient…