Approximate iterations in Bregman-function-based proximal algorithms
This paper establishes convergence of generalized Bregman-function-based proximal point algorithms when the iterates are computed only approximately. The problem being solved is modeled as a general maximal monotone operator, and need not reduce to minimization of a function. The accuracy conditions on the iterates resemble those required for the classical “linear” proximal point algorithm, but are slightly stronger; they should be easier to verify or enforce in practice than conditions given in earlier analyses of approximate generalized proximal methods. Subjects to these practically enforceable accuracy restrictions, convergence is obtained under the same conditions currently established for exact Bregman-function-based proximal methods.
KeywordsProximal algorithms Bregman functions Monotone operators
Unable to display preview. Download preview PDF.
- H. Brézis, Opérateurs Maximaux Monotones et Semi-Groups de Contractions dans les Espaces de Hilbert, North-Holland, Amsterdam, 1973.Google Scholar
- R. S. Burachik, A. N. Iusem, A generalized proximal point algorithm for the variational inequality problem in Hilbert space, Working Paper, Instituto de Matemática Pura e Aplicada, Rio de Janeiro, 1995.Google Scholar
- Y. Censor, A. N. Iusem, S. A. Zenios, An interior-point method with Bregman functions for the variational inequality problem with paramonotone operators, Working Paper, University of Haifa, 1994.Google Scholar
- J. Eckstein, M. C. Ferris, Smooth methods of multipliers for monotone complementarity problems, RUTCOR Research Report RRR 27–96, Rutgers University, 1996, revised 1997.Google Scholar
- S. Kabbadj, Methodes Proximales Entopiques, Doctoral Thesis, Université de Montpellier II–Sciences et Techniques du Languedoc, 1994.Google Scholar
- B. Polyak, Introduction to Optimization, Optomization Softwave Inc., New York, 1987.Google Scholar
- M. Teboulle, Convergence of proximal-like algorithms, SIAM Journal of Optimization (to appear).Google Scholar