Smooth Nonconvex Banach-Space Optimization
Descriptions may be stale. Consult the linked Lean sources.
Smooth Nonconvex
Banach-Space Optimization
We consider minimizing a possibly nonconvex function on a real Banach space
. Its Fréchet derivative , where is the continuous dual of , is -Lipschitz in the induced operator norm
, with . A given point has objective gap at most above a global lower bound.
The oracle returns at
. For , the goal is a
measurable output
satisfying ,
where is the law of the
algorithm’s randomness.
The optimization problem is The space is
equipped with a specified measurable structure. We write for its norm and use the
induced operator norm on . The
algorithm receives , , , , and .
Our assumptions:
Assumption 1 (Smoothness). The function is Fréchet differentiable everywhere on
, and
Assumption 2 (Initial objective gap). There exists
such that
Queries may be made at any point of , with exact derivative replies in . After the allotted oracle calls, the
output must be measurable,
its squared derivative norm must be integrable under , and it must satisfy
Results
Lean setup