Hessian Only Finite Sum Third Smooth — Finite-Sum Convex Third-Order Smoothness
Descriptions may be stale. Consult the linked Lean sources.
Finite-Sum Convex Third-Order Smoothness · Lean proof
Finite-Sum Convex
Third-Order Smoothness
We consider minimizing on a
finite-dimensional real inner-product space , where is an integer. Each component
is convex and
three times continuously differentiable, with -Lipschitz third derivative, where . A given point lies within distance of a minimizer ; its objective gradient and
Hessian have norms bounded by , respectively. A query returns . For
, the goal is a
measurable output
satisfying ,
where is the law of the
algorithm’s randomness.
The optimization problem is The norm is induced by the inner product
on . Derivative norms are the induced
operator norms: the Hessian acts from to , and the third derivative is a
trilinear form on . The algorithm
receives ,
and .
Our assumptions:
Assumption 1 (Component convexity and regularity).
For every , the
function belongs to , and for all and ,
Its third derivative satisfies
Assumption 2 (Minimizer and initial bounds). The
instance specifies a point such that
The oracle accepts any component index and any point , returning the exact component
gradient and Hessian together in one call. After the allotted calls, the
output must be measurable
with respect to the Borel sets of
and satisfy
Proved result
OracleTemplate.Convergence LongTails.Setups.FiniteSumThirdSmoothConvex.spec
LongTails.Theorems.HessianOnlyFiniteSumThirdSmooth.budget
Relevant previous results
No qualifying prior reference verified; this is not a proof of novelty.