Set-valued regression and cautious suboptimization: From noisy data to optimality
Metadata only
Datum
2024-01-19Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
This paper deals with the problem of finding suboptimal values of an unknown function on the basis of measured data corrupted by bounded noise. As a prior, we assume that the unknown function is parameterized in terms of a number of basis functions. Inspired by the informativity approach, we view the problem as the suboptimization of the worst-case estimate of the function. The paper provides closed form solutions and convexity results for this function, which enables us to solve the problem. After this, an online implementation is investigated, where we iteratively measure the function and perform a suboptimization. This nets a procedure that is safe at each step, and which, under mild assumptions, converges to the true optimizer. Mehr anzeigen
Publikationsstatus
publishedExterne Links
Buchtitel
2023 62nd IEEE Conference on Decision and Control (CDC)Seiten / Artikelnummer
Verlag
IEEEKonferenz
Organisationseinheit
02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.
Förderung
203979 - From model-based to data-driven design: Signal processing and control of noisy nonlinear systems (SNF)
Anmerkungen
Conference lecture held on December 14, 2023.ETH Bibliographie
yes
Altmetrics