Descriptions may be stale. Consult the linked Lean sources.
Stochastic Cohypomonotone
Inclusions
We consider solving in a finite-dimensional real inner product space
, where is -Lipschitz and is monotone. The
sum is -cohypomonotone, with , , and . A given point lies within distance of a solution. The oracle returns
unbiased estimates of with
independent sampling and variance at most , where , or exact resolvent
evaluations of . For , the goal is a
measurable pair
with for
every realization and ,
averaging over sampling and algorithm randomness.
The inclusion problem is to find such that Write for the inner
product and for its
induced norm. The algorithm receives , the measurable sample space , , , , , , and .
Our assumptions:
Assumption 1 (Lipschitz continuity and
cohypomonotonicity). For every , For every and ,
monotonicity of and
cohypomonotonicity of mean
Assumption 2 (Initial distance). There exists satisfying
Assumption 3 (Stochastic operator access). There is
a probability measure on and a jointly measurable map . For each , the map is Bochner integrable and
is integrable
under , with The samples are measurable, mutually
independent, and each has law .
They are independent of the algorithm’s randomness. A stochastic query
at on call returns .
Assumption 4 (Exact resolvent access). There is a
map such
that, for every and
, A resolvent query returns
exactly. The stated
resolvent condition applies to positive .
Each call chooses either a stochastic query or a resolvent query;
both count toward the same total oracle-call budget. The index counts calls of either kind.
The output must be measurable and satisfy for every
realization. Its residual norm must be integrable and obey
where is the joint law of the
oracle samples and the independent algorithm randomness.