Showing 2023Show all
2 papers · 1 filter
math.OC2023
Optimal and parameter-free gradient minimization methods for convex and nonconvex optimization
Guanghui Lan, Yuyuan Ouyang, Zhe Zhang
We propose novel optimal and parameter-free algorithms for computing an approximate solution with small (projected) gradient norm. Specifically, for computing an approximate soluti…
math.OC2023
A simple uniformly optimal method without line search for convex optimization
Tianjiao Li, Guanghui Lan
Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem paramete…