E. Guerre et Ab. Tsybakov, EXACT ASYMPTOTIC MINIMAX CONSTANTS FOR THE ESTIMATION OF ANALYTICAL FUNCTIONS IN L-P, Probability theory and related fields, 112(1), 1998, pp. 33-51
The L-p minimax risks (1 less than or equal to p < infinity) are studi
ed for statistical estimation in the Gaussian white noise model. The a
symptotic rate and constants are given, and the optimal estimator is p
roposed. This, together with the work of Golubev, Levit and Tsybakov (
1996) establishes the classification of the L-p minimax constants on t
he classes of analytical functions.