Generalized Smooth Convex Minimization
Descriptions may be stale. Consult the linked Lean sources.
Generalized Smooth Convex Minimization
We consider minimizing a convex function
The optimization problem is
Our assumptions:
Assumption 1 (Convexity). For every
Assumption 2 (Generalized smoothness). The function
Assumption 3 (Initial distance). There exists
Queries may be made at any point of
Results
Convex
| Result | Oracle complexity | Novelty | Limitations |
|---|---|---|---|
| (1) RadiusFreeGeneralizedAccelerated
(Ours) |
|||
| (2) SHERPA+CRUISE (Rudomanov et al. 2026), Thm. 3.7 | (1): Matches known rate;
needs neither |
(1): Larger proved numerical constants. | |
| (3) (Tyurin 2026),
Thm. 4.3; finite-dimensional restriction; |
(1): No |
||
| (4) Backtracking accelerated (LongTails, n.d.) | (1): Removes gap
dependence. For |
(1) needs |
Abbr: