Univ. Heidelberg
Statistics Group   Institute for Mathematics   Faculty of Mathematics and Computer Science   University Heidelberg
Ruprecht-Karls-Universität Heidelberg Institute for Mathematics Statistics of inverse problems Research Group
german english french



Publications
Cooperations
Research projects
Events
Teaching
Completed theses
People
Contact


Last edited on
Jun 20, 2025 by JJ
.
Thesis:
Master in Mathematics

Author:
Janina Rastetter

Title:
Optimale verteilte Schätzung bei beschränktem Kommunikationsbudget

Supervisors:
Jan JOHANNES

Abstract:
Distributed minimax estimation under communication constraints for Gaussian sequence model is examined. Basics in information theory are provided to motivate and present an algorithm using a uniquely decodable encoding function. The expected costs of the algorithm remain below the communication budget. An upper bound for a specific estimator and a lower bound are proven resulting in the minimax rate of convergence with respect to the mean squared error for distributed estimation over a given Besov class.

Reference:
T. T. Cai und H. Wei. Distributed nonparametric function estimation: optimal rate of convergence and cost of adaptation, The Annals of Statistics, 50(2):698–725, 2022.