Följ
Naoki Sato
Naoki Sato
Meiji University
Verifierad e-postadress på iiduka.net
Titel
Citeras av
Citeras av
År
Existence and estimation of critical batch size for training generative adversarial networks with two time-scale update rule
N Sato, H Iiduka
International Conference on Machine Learning, 30080-30104, 2023
32023
Using stochastic gradient descent to smooth nonconvex functions: Analysis of implicit graduated optimization with optimal noise scheduling
N Sato, H Iiduka
arXiv preprint arXiv:2311.08745, 2023
12023
Role of Momentum in Smoothing Objective Function in Implicit Graduated Optimization
N Sato, H Iiduka
arXiv preprint arXiv:2402.02325, 2024
2024
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–3