Showing math.OCShow all
2 papers · 1 filter
math.OC2025
Lyapunov Analysis For Monotonically Forward-Backward Accelerated Algorithms
Mingwei Fu, Bin Shi
Nesterov's accelerated gradient method (NAG) achieves faster convergence than gradient descent for convex optimization but lacks monotonicity in function values. To address this, B…
math.OC2025
A Family of Controllable Momentum Coefficients for Forward-Backward Accelerated Algorithms
Mingwei Fu, Bin Shi
Nesterov's accelerated gradient method (NAG) marks a pivotal advancement in gradient-based optimization, achieving faster convergence compared to the vanilla gradient descent metho…