Stebėti
Bingrui Li
Pavadinimas
Cituota
Cituota
Metai
Memory Efficient Optimizers with 4-bit States
B Li, J Chen, J Zhu
Advances in Neural Information Processing Systems 36, 2023
292023
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
B Li, W Huang, A Han, Z Zhou, T Suzuki, J Zhu, J Chen
arXiv preprint arXiv:2410.04870, 2024
12024
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
Z Zhou, M Wang, Y Mao, B Li, J Yan
arXiv preprint arXiv:2410.10373, 2024
2024
Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.
Straipsniai 1–3