A Novel Sine Step Size for Warm-Restart Stochastic Gradient Descent
This paper proposes a novel sine step size for warm-restart stochastic gradient descent (SGD). For the SGD based on the new proposed step size, we establish convergence rates for smooth non-convex functions with and without the Polyak–Łojasiewicz (PL) condition. To assess the effectiveness of the ne...
Gorde:
| Egile Nagusiak: | , |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
MDPI AG
2024-12-01
|
| Saila: | Axioms |
| Gaiak: | |
| Sarrera elektronikoa: | https://www.mdpi.com/2075-1680/13/12/857 |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|