Fast convergence of the expectation-maximization algorithm under a logarithmic Sobolev inequality

R Caprio and A M Johansen

Biometrika, 2025, vol. 112, issue 4, asaf061.

Abstract: SummaryWe present a new framework for analysing the expectation-maximization (em) algorithm. Drawing on recent advances in the theory of gradient flows over Euclidean–Wasserstein spaces, we extend techniques from alternating minimization in Euclidean spaces to the em algorithm, via its representation as coordinatewise minimization of the free energy. In so doing, we obtain finite-sample error bounds and exponential convergence of the em algorithm under a natural generalization of the log-Sobolev inequality. We further show that this framework naturally extends to several variants of the em algorithm, offering a unified approach for studying such algorithms.

Keywords: Empirical Bayes framework; Expectation-maximization algorithm; First-order em algorithm; Functional inequality; Latent variable model; Log-Sobolev inequality; Maximum likelihood estimator; Non-asymptotic bound; Wasserstein gradient (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/biomet/asaf061 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:biomet:v:112:y:2025:i:4:p:asaf061.

Ordering information: This journal article can be ordered from
https://academic.oup.com/journals

Access Statistics for this article

Biometrika is currently edited by Paul Fearnhead

More articles in Biometrika from Biometrika Trust Oxford University Press, Great Clarendon Street, Oxford OX2 6DP, UK.
Bibliographic data for series maintained by Oxford University Press ().