Universal confidence sets - sufficient conditions

Vogel, Silvia GND

Universal confidence sets for solutions of optimization problems are sequences of random sets (C_n)_{n \in N} with the property that for each sample size n the set C_n covers the true solution at least with a prescribed probability. Universal confidence sets can be derived making use of uniform concentration-of-measure results for sequences of random functions and knowledge about the limit problem, e.g. a growth condition. We present sufficient conditions for the convergence assumptions and show how estimates for the growth function can be included.

Cite

Citation style:
Vogel Prof. Dr. rer. nat. habil., S., 2008. Universal confidence sets - sufficient conditions. Preprint /  Technische Universität Ilmenau, Institut für Mathematik, Preprint /  Technische Universität Ilmenau, Institut für Mathematik 08–06.
Could not load citation form. Default citation form is displayed.

Rights

Use and reproduction:
All rights reserved

Export