Minimax spectral-density estimation under local differential privacy for dependent Gaussian data
Statement
Let be observations from a centered stationary Gaussian process with spectral density belonging to a Sobolev-type class , and let the observations be released through an -locally differentially private mechanism, possibly interactive. Determine the minimax estimation risk as a function of , , and the smoothness parameters. In particular, determine whether, in the high-privacy regime, the effective sample size is rather than because of temporal dependence.
Record
- Added
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 inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.