Convergence of an alternating maximization procedure

Andreas Andresen, Vladimir Spokoiny

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)


We derive two convergence results for a sequential alternating maximization procedure to approximate the maximizer of random functionals such as the realized log likelihood in MLE estimation. We manage to show that the sequence attains the same deviation properties as shown for the profile M-estimator by Andresen and Spokoiny (2013), that means a finite sample Wilks and Fisher theorem. Further under slightly stronger smoothness constraints on the random functional we can show nearly linear convergence to the global maximizer if the starting point for the procedure is well chosen.

Original languageEnglish
JournalJournal of Machine Learning Research
Publication statusPublished - 1 Apr 2016
Externally publishedYes


  • Alternating maximization
  • Alternating minimization
  • EM-algorithm
  • Local concentration
  • Local linear approximation
  • M-estimation
  • Profile maximum likelihood
  • Semi-parametric


Dive into the research topics of 'Convergence of an alternating maximization procedure'. Together they form a unique fingerprint.

Cite this