Inexact Augmented Lagrangian Methods for Conic Programs: Quadratic Growth and Linear Convergence
–Neural Information Processing Systems
Under the quadratic growth assumption, it is known that the dual iterates and the Karush-Kuhn-Tucker (KKT) residuals of ALMs applied to semidefi-nite programs (SDPs) converge linearly. In contrast, the convergence rate of the primal iterates has remained elusive.
Neural Information Processing Systems
Nov-16-2025, 23:19:41 GMT
- Country:
- Asia
- China (0.04)
- Middle East > Jordan (0.04)
- Europe > Spain
- Aragón (0.04)
- North America > United States
- California
- San Diego County > San Diego (0.04)
- Santa Clara County > Palo Alto (0.04)
- California
- Asia
- Genre:
- Research Report > Experimental Study (0.92)
- Technology: