The regularized feasible directions method for nonconvex optimization

Amir Beck*, Nadav Hallak

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


This paper develops and studies a feasible directions approach for the minimization of a continuous function over linear constraints in which the update directions belong to a predetermined finite set spanning the feasible set. These directions are recurrently investigated in a cyclic semi-random order, where the stepsize of the update is determined via univariate optimization. We establish that any accumulation point of this optimization procedure is a stationary point of the problem, meaning that the directional derivative in any feasible direction is nonnegative. To assess and establish a rate of convergence, we develop a new optimality measure that acts as a proxy for the stationarity condition, and substantiate its role by showing that it is coherent with first-order conditions in specific scenarios. Finally we prove that our method enjoys a sublinear rate of convergence of this optimality measure in expectation.

Original languageEnglish
Pages (from-to)517-523
Number of pages7
JournalOperations Research Letters
Issue number5
StatePublished - Sep 2022


  • Constrained optimization
  • Convergence analysis
  • Feasible directions
  • Nonconvex optimization
  • Nonsmooth optimization


Dive into the research topics of 'The regularized feasible directions method for nonconvex optimization'. Together they form a unique fingerprint.

Cite this