Generalized Smooth Composite Minimization
Descriptions may be stale. Consult the linked Lean sources.
Generalized Smooth Composite Minimization
We minimize
The optimization problem is
Our assumptions:
Assumption 1 (Convexity and Lipschitz regularizer).
For every
Assumption 2 (Generalized smoothness). The function
Assumption 3 (Exact proximal minimization). There is
a map
Assumption 4 (Initial distance). There exists
The oracle returns
After the allotted calls, the output must satisfy
Results
On a real Hilbert space, minimize
| Result | Oracle complexity | Novelty | Limitations |
|---|---|---|---|
| (1) LipschitzCompositeGeneralizedAccelerated
(Ours) |
|||
| (2) (Li et al. 2026), v3, Theorem 8 (upper bound) | (1): transient |
(1) needs |
|
| (3) Derived bound: Moreau smoothing and regularization, then (Rudomanov et al. 2026), Theorem 3.7 | (1) removes |
(1) additionally needs
|
|
| (4) (Rudomanov et al. 2026), v2, Theorem 3.7 | (1): Scope:
Lipschitz-composite objectives. Matches known rate on the overlap;
updates need neither |
Abbr: