3 papers
math.OC2024
A template for gradient norm minimization
Mihai I. Florea
The gradient mapping norm is a strong and easily verifiable stopping criterion for first-order methods on composite problems. When the objective exhibits the quadratic growth prope…
math.OC2024
Adaptive first-order methods with enhanced worst-case rates
Mihai I. Florea
The Optimized Gradient Method (OGM), its strongly convex extension, the Information Theoretical Exact Method (ITEM), as well as the related Triple Momentum Method (TMM) have superi…
math.OC2024
An optimal lower bound for smooth convex functions
Mihai I. Florea, Yurii Nesterov
First order methods endowed with global convergence guarantees operate using global lower bounds on the objective. The tightening of the bounds has been shown to increase both the…