"deep learning optimization" Papers
3 papers found
Prodigy: An Expeditiously Adaptive Parameter-Free Learner
Konstantin Mishchenko, Aaron Defazio
ICML 2024poster
QLABGrad: A Hyperparameter-Free and Convergence-Guaranteed Scheme for Deep Learning
Fang-Xiang Wu, Minghan Fu
AAAI 2024paperarXiv:2302.00252
11
citations
Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens
Ross Clarke, Jose Miguel Hernandez-Lobato
ICML 2024poster