ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let X1,…,XNX_1,\ldots,X_N be observations from a centered stationary Gaussian process with spectral density ff belonging to a Sobolev-type class Fs\mathcal F_s, and let the observations be released through an α\alpha-locally differentially private mechanism, possibly interactive. Determine the minimax L2L_2 estimation risk inf⁡Q,f^sup⁡f∈FsEf[∥f^−f∥22]\inf_{Q,\widehat f}\sup_{f\in\mathcal F_s}\mathbb E_f\left[\lVert\widehat f-f\rVert_2^2\right] as a function of NN, α\alpha, and the smoothness parameters. In particular, determine whether, in the high-privacy regime, the effective sample size is Nα4N\alpha^4 rather than Nα2N\alpha^2 because of temporal dependence.

Record

Added
Links

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.