The Efficiency of subgradient projection methods for convex nondifferentiable optimization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1993

The Efficiency of subgradient projection methods for convex nondifferentiable optimization

Abstract

We study subgradient methods for convex optimization that use projections onto successive approximations of level sets of the objective corresponding to estimates of the optimal value. We show that they enjoy almost optimal efficiency estimates. We present several variants, establish their efficiency estimates and discuss possible implementations. In particular, their projection subproblems may be solved inexactly via relaxation methods, thus opening the way for parallel implementations. We discuss accelerations of relaxation methods based on simultaneous projections, surrogate constraints and conjugate and projected (conditional) subgradient techniques.

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-1845.pdf (2.05 Mo) Télécharger le fichier

Dates and versions

inria-00074827 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00074827 , version 1

Cite

Krzysztof C. Kiwiel. The Efficiency of subgradient projection methods for convex nondifferentiable optimization. [Research Report] RR-1845, INRIA. 1993. ⟨inria-00074827⟩
81 View
45 Download

Share

Gmail Facebook X LinkedIn More