ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let

ΔK={(p0,…,pK−1):pk≥0 ∀k, ∑kpk=1}.\Delta_K=\left\{(p_0,\ldots,p_{K-1}):p_k\ge 0\ \forall k,\ \sum_k p_k=1\right\}.

For the loss

L(p⃗,p⃗^)=1−B(p⃗,p⃗^)2,B(p⃗,p⃗^)=∑kpkp^k,L(\vec p,\hat{\vec p})=1-B(\vec p,\hat{\vec p})^2, \qquad B(\vec p,\hat{\vec p})=\sum_k\sqrt{p_k\hat p_k},

the Bayes estimator is

p⃗^=(a02,a12,…,aK−12),\hat{\vec p}=(a_0^2,a_1^2,\ldots,a_{K-1}^2),

where a⃗=(a0,a1,…,aK−1)\vec a=(a_0,a_1,\ldots,a_{K-1}) is the eigenvector associated with the maximal eigenvalue of the matrix whose entries are

Ep⃗ ⁣[pjpk],\mathbb E_{\vec p}\!\left[\sqrt{p_jp_k}\right],

with the expectation taken with respect to the posterior distribution of p⃗\vec p.

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.