Local convergence of proximal splitting methods for rank constrained problems

Christian Grussler, Pontus Giselsson

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

Sammanfattning

We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hence implying local convergence. The conditions imply that the non-convex algorithms locally converge to a solution whenever a convex relaxation involving the convex envelope can be expected to solve the non-convex problem.

Originalspråkengelska
Titel på värdpublikation2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Sidor702-708
Antal sidor7
Volym2018-January
ISBN (elektroniskt)9781509028733
DOI
StatusPublished - 2018 jan. 18
Evenemang56th IEEE Annual Conference on Decision and Control, CDC 2017 - Melbourne, Australien
Varaktighet: 2017 dec. 122017 dec. 15
Konferensnummer: 56
http://cdc2017.ieeecss.org/

Konferens

Konferens56th IEEE Annual Conference on Decision and Control, CDC 2017
Förkortad titelCDC 2017
Land/TerritoriumAustralien
OrtMelbourne
Period2017/12/122017/12/15
Internetadress

Ämnesklassifikation (UKÄ)

  • Reglerteknik

Fingeravtryck

Utforska forskningsämnen för ”Local convergence of proximal splitting methods for rank constrained problems”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här