A Momentum-Based Adaptive Primal–Dual Stochastic Gradient Method for Non-Convex Programs with Expectation Constraints
In this paper, we propose a stochastic primal-dual adaptive method based on an inexact augmented Lagrangian function to solve non-convex programs, referred to as the SPDAM. Different from existing methods, SPDAM incorporates adaptive step size and momentum-based search directions, which improve the...
Kaydedildi:
| Asıl Yazarlar: | , , |
|---|---|
| Materyal Türü: | Artigo |
| Dil: | Inglês |
| Baskı/Yayın Bilgisi: |
MDPI AG
2024-07-01
|
| Seri Bilgileri: | Mathematics |
| Konular: | |
| Online Erişim: | https://www.mdpi.com/2227-7390/12/15/2393 |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|