Showing 2026Show all
2 papers · 1 filter
math.OC2026
Improved Gradient Complexity for Quasi-Newton Proximal Extragradient Methods via Certified Curvature Reuse
Aryan Mokhtari, Francisco Patitucci
We study how curvature estimated from gradient differences can accelerate proximal-extragradient quasi-Newton methods. Existing global guarantees for QNPE, A-QNPE, and OL-OQN learn…
cs.LG2026
Adaptive Optimization via Momentum on Variance-Normalized Gradients
Francisco Patitucci, Aryan Mokhtari
We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-ba…