← All setups

Radius Free Generalized Accelerated — Generalized Smooth Convex Minimization

Descriptions may be stale. Consult the linked Lean sources.

Generalized Smooth Convex Minimization · Lean proof

Generalized Smooth Convex Minimization

We consider minimizing a convex function f:E→R on a real Hilbert space E. The function f is (L0,L1)-smooth, with L0>0 and L1>0, and has an everywhere differentiable gradient. A given starting point x0∈E lies within distance R>0 of a global minimizer x⋆. The oracle returns ∇f(x) at x. For a tolerance ε>0, the goal is an output x¯∈E satisfying f(x¯)−f(x⋆)≤ε almost surely under P, the law of the algorithm’s randomness.

The optimization problem is minx∈Ef(x). The norm ∥⋅∥ is induced by the inner product on E, and ∥⋅∥op denotes the induced operator norm. The algorithm receives only E, L0, L1, and x0; the radius R and tolerance ε may enter the oracle-call budget but are not algorithm inputs.

Our assumptions:

Assumption 1 (Convexity). For every x,y∈E and t∈[0,1], f((1−t)x+ty)≤(1−t)f(x)+tf(y).

Assumption 2 (Generalized smoothness). The function f and its gradient ∇f:E→E are Fréchet differentiable everywhere. The Hessian ∇2f(x):E→E satisfies ∥∇2f(x)∥op≤L0+L1∥∇f(x)∥,x∈E.

Assumption 3 (Initial distance). There exists x⋆∈E such that f(x⋆)≤f(x)for every x∈E,∥x0−x⋆∥≤R.

Queries may be made at any point of E. After the allotted oracle calls, the output must satisfy f(x¯)−f(x⋆)≤εP-a.s. Here x⋆ is fixed independently of the algorithm’s randomness; all global minimizers have the same objective value.

Proved result

⌈64⋅L0⋅R2ε+32768⋅(1+L1⋅R)⋅log⁡(2+L1⋅R)⌉+

OracleTemplate.Convergence LongTails.Setups.RadiusOnlyGeneralizedSmoothConvex.spec
  OracleTemplate.RadiusFreeSherpa.budget

Relevant previous results