padam

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

Partially Adaptive Momentum Estimation method in the paper "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks" (accepted by IJCAI 2020)

PyTorch repository for text categorization and NER experiments in Turkish and English.

PADAM Optimizer - Python Implementation