Exponential Convergence of General Iterative Proportional Fitting Procedures
SIAM Journal on Optimization · 30.06.2026 · 36 (2) · 912-937
DOI: 10.1137/25m1752584 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 27.05.2026. Verfasst von Stephan Eckstein und 1 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Cluster of Excellence, Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
Motivated by the success of Sinkhorn’s algorithm for entropic optimal transport, we study convergence properties of iterative proportional fitting procedures (IPFP) used to solve more general information projection problems. We establish exponential convergence guarantees for the IPFP whenever the set of probability measures which is projected onto is defined through constraints arising from linear function spaces. This unifies and extends recent results from multimarginal, adapted, and martingale optimal transport. The proofs are based on strong convexity arguments for the dual problem, and the key contribution is to illuminate the role of the geometric interplay between the subspaces defining the constraints. In this regard, we show that the larger the angle (in the sense of Friedrichs) between the linear function spaces, the better the rate of contraction of the IPFP.
Förderung
- Cluster of Excellence
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Eckstein, S., & Lakhal, A. (2026). Exponential Convergence of General Iterative Proportional Fitting Procedures. SIAM Journal on Optimization, 36(2), 912-937. https://doi.org/10.1137/25m1752584
Vancouver
Eckstein S, Lakhal A. Exponential Convergence of General Iterative Proportional Fitting Procedures. SIAM Journal on Optimization. 2026;36(2):912-937. doi:10.1137/25m1752584
BibTeX
@article{Eckstein2026,
author = {Eckstein, Stephan and Lakhal, Aziz},
title = {Exponential Convergence of General Iterative Proportional Fitting Procedures},
journal = {SIAM Journal on Optimization},
year = {2026},
volume = {36},
number = {2},
pages = {912--937},
doi = {10.1137/25m1752584}
}
EUVIMED