MSDF-SGD: Most-Significant Digit-First Stochastic Gradient Descent for Arbitrary-Precision Training.
Changjun Song, Yongming Tang, Jiyuan Liu, Sige Bian, Danni Deng, He Li
Browse the full FPL paper archive.
Changjun Song, Yongming Tang, Jiyuan Liu, Sige Bian, Danni Deng, He Li
Browse the full FPL paper archive.