@article{adalossacomputationallyefficientand, title = {AdaLoss: A computationally-efficient and provably convergent adaptive gradient method}, author = {Xiaoxia Wu and Yuege Xie and Simon Du and Rachel Ward}, year = {2021}, eprint = {2109.08282}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2109.08282v1}, }