Article Dans Une Revue Electronic Journal of Statistics Année : 2020

On polyhedral estimation of signals via indirect observations

Résumé

We consider the problem of recovering linear image of unknown signal belonging to a given convex compact signal set from noisy observation of another linear image of the signal. We develop a simple generic efficiently computable nonlinear in observations “polyhedral” estimate along with computation-friendly techniques for its design and risk analysis. We demonstrate that under favorable circumstances the resulting estimate is provably near-optimal in the minimax sense, the “favorable circumstances” being less restrictive than the weakest known so far assumptions ensuring near-optimality of estimates which are linear in observations.
Fichier principal
Vignette du fichier
1803.06446v2.pdf (861) Télécharger le fichier
Origine Publication financée par une institution

Dates et versions

hal-03185487 , version 1 (07-01-2025)

Identifiants

Citer

Anatoli B. Juditsky, Arkadi Nemirovski. On polyhedral estimation of signals via indirect observations. Electronic Journal of Statistics , 2020, 14 (1), pp.458-502. ⟨10.1214/19-EJS1661⟩. ⟨hal-03185487⟩
45 Consultations
2 Téléchargements

Altmetric

Partager

More