Alternating Bregman projections and convergence of the EM algorithm
Statistics Theory
2025-07-30 v1 Statistics Theory
Abstract
We investigate convergence of alternating Bregman projections between non-convex sets and prove convergence to a point in the intersection, or to points realizing a gap between the two sets. The speed of convergence is generally sub-linear, but may be linear under transversality. We apply our analysis to prove convergence of versions of the expectation maximization algorithm for non-convex parameter sets.
Cite
@article{arxiv.2507.21840,
title = {Alternating Bregman projections and convergence of the EM algorithm},
author = {Dominikus Noll},
journal= {arXiv preprint arXiv:2507.21840},
year = {2025}
}