Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

Quasi-Newton Methods: A New Direction

MPG-Autoren
/persons/resource/persons84387

Hennig,  P
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

/persons/resource/persons84384

Kiefel,  M
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

Externe Ressourcen
Volltexte (beschränkter Zugriff)
Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte in PuRe verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Hennig, P., & Kiefel, M. (2012). Quasi-Newton Methods: A New Direction. In J. Langford, & J. Pineau (Eds.), 29th International Conference on Machine Learning (ICML 2012) (pp. 25-32). Madison, WI, USA: International Machine Learning Society.


Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0013-B6CA-1
Zusammenfassung
Four decades after their invention, quasi- Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that t a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more ecient use of available information at computational cost similar to its predecessors.