Mathematical Programming

, Volume 146, Issue 1–2, pp 37–75

First-order methods of smooth convex optimization with inexact oracle

  • Olivier Devolder
  • François Glineur
  • Yurii Nesterov
Full Length Paper Series A

DOI: 10.1007/s10107-013-0677-5

Cite this article as:
Devolder, O., Glineur, F. & Nesterov, Y. Math. Program. (2014) 146: 37. doi:10.1007/s10107-013-0677-5

Abstract

We introduce the notion of inexact first-order oracle and analyze the behavior of several first-order methods of smooth convex optimization used with such an oracle. This notion of inexact oracle naturally appears in the context of smoothing techniques, Moreau–Yosida regularization, Augmented Lagrangians and many other situations. We derive complexity estimates for primal, dual and fast gradient methods, and study in particular their dependence on the accuracy of the oracle and the desired accuracy of the objective function. We observe that the superiority of fast gradient methods over the classical ones is no longer absolute when an inexact oracle is used. We prove that, contrary to simple gradient schemes, fast gradient methods must necessarily suffer from error accumulation. Finally, we show that the notion of inexact oracle allows the application of first-order methods of smooth convex optimization to solve non-smooth or weakly smooth convex problems.

Keywords

Smooth convex optimization First-order methods Inexact oracle Gradient methods Fast gradient methods Complexity bounds 

Mathematics Subject Classification (2000)

90C06 90C25 90C60 

Copyright information

© Springer-Verlag Berlin Heidelberg and Mathematical Optimization Society 2013

Authors and Affiliations

  • Olivier Devolder
    • 1
  • François Glineur
    • 1
  • Yurii Nesterov
    • 1
  1. 1.Université catholique de Louvain, ICTEAM Institute/CORELouvain-la-NeuveBelgium

Personalised recommendations