Generalized Gradient Flows with Provable Fixed-Time Convergence and Fast Evasion of Non-Degenerate Saddle Points

no code implementations • 7 Dec 2022 • Mayank Baranwal, Param Budhraja, Vishal Raj, Ashish R. Hota

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks.