Showing math.OCShow all
3 papers · 1 filter
math.OC2026
Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes
Yu Liu, Kang Chen, Rujun Jiang +1
Predetermined stepsize schedules featuring carefully chosen long steps have recently been shown to accelerate gradient descent (GD) on smooth convex functions. A prominent class of…
math.OC2024
Zeroth-order Stochastic Cubic Newton Method Revisited
Yu Liu, Weibin Peng, Tianyu Wang +1
This paper studies stochastic minimization of a finite-sum loss . In many real-world scenarios, the Hessian matrix of s…
math.OC2023
The Nesterov-Spokoiny Acceleration Achieves Strict Convergence
Weibin Peng, Yu Liu, Tianyu Wang
This paper studies the Nesterov-Spokoiny Acceleration (NSA), a variant of the accelerated gradient method by Nesterov and Spokoiny. For smooth convex optimization, NSA achieves a s…