ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let qq and q~\tilde q be the distributions produced by the inner-loop optimization, and let η\eta and η~\tilde\eta be the corresponding expectation parameters for the marginal distributions on YY and ZZ. The quantities ∥q~−q∥∞\|\tilde q-q\|_\infty and ∥η~−η∥1\|\tilde\eta-\eta\|_1 measure the approximation errors in the distribution and expectation parameters, respectively.

Inner-loop error-bound conjecture.

∥q~−q∥∞≤∥η~−η∥1.\|\tilde q-q\|_\infty \leq \|\tilde\eta-\eta\|_1.

This bound would provide the criterion needed to interrupt the inner iteration while guaranteeing a prescribed accuracy for the computed distribution. The supplied text does not indicate whether the claim has been proved or remains open.

Record

Comments

Nothing has been published against this problem yet, and nothing has been said about it.

Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.

Sign in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.