Faster subgradient methods for functions with Hölderian growth

Patrick R. Johnstone, Pierre Moulin

Research output: Contribution to journalArticlepeer-review


The purpose of this manuscript is to derive new convergence results for several subgradient methods applied to minimizing nonsmooth convex functions with Hölderian growth. The growth condition is satisfied in many applications and includes functions with quadratic growth and weakly sharp minima as special cases. To this end there are three main contributions. First, for a constant and sufficiently small stepsize, we show that the subgradient method achieves linear convergence up to a certain region including the optimal set, with error of the order of the stepsize. Second, if appropriate problem parameters are known, we derive a decaying stepsize which obtains a much faster convergence rate than is suggested by the classical O(1/k) result for the subgradient method. Thirdly we develop a novel “descending stairs” stepsize which obtains this faster convergence rate and also obtains linear convergence for the special case of weakly sharp functions. We also develop an adaptive variant of the “descending stairs” stepsize which achieves the same convergence rate without requiring an error bound constant which is difficult to estimate in practice.

Original languageEnglish (US)
Pages (from-to)417-450
Number of pages34
JournalMathematical Programming
Issue number1-2
StatePublished - Mar 1 2020

ASJC Scopus subject areas

  • Software
  • General Mathematics


Dive into the research topics of 'Faster subgradient methods for functions with Hölderian growth'. Together they form a unique fingerprint.

Cite this