TU Berlin

Methoden der Künstlichen IntelligenzPublikationen

Inhalt des Dokuments

zur Navigation

Prof. Dr. Manfred Opper

  • Leiter der Einheit KI
  • Raum: MAR 4.017
  • Telefon: +4930 314-73749
  • E-Mail: manfred.opper <AT> tu-berlin.de



Sprechstunde nach Vereinbarung


Dynamical Functional Theory for Compressed Sensing
Zitatschlüssel CaOpWiFle17
Autor Burak Çakmak and Manfred Opper and Ole Winther and Bernard H. Fleury
Seiten 2143-2147
Jahr 2017
DOI 10.1109/ISIT.2017.8006908
Journal 2017 IEEE International Symposium on Information Theory (ISIT)
Verlag IEEE Press
Zusammenfassung We introduce a theoretical approach for designing generalizations of the approximate message passing (AMP) algorithm for compressed sensing which are valid for large observation matrices that are drawn from an invariant random matrix ensemble. By design, the fixed points of the algorithm obey the Thouless-Anderson-Palmer (TAP) equations corresponding to the ensemble. Using a dynamical functional approach we are able to derive an effective stochastic process for the marginal statistics of a single component of the dynamics. This allows us to design memory terms in the algorithm in such a way that the resulting fields become Gaussian random variables allowing for an explicit analysis. The asymptotic statistics of these fields are consistent with the replica ansatz of the compressed sensing problem.
Download Bibtex Eintrag



Schnellnavigation zur Seite über Nummerneingabe