@article{onexploitinglayerwisegradientstatistics, title = {A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range}, author = {Guoqiang Zhang and Kenta Niwa and W. Bastiaan Kleijn}, year = {2022}, eprint = {2203.13273}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2203.13273v5}, }