English

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.

Keywords

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}
}
R2 v1 2026-07-01T04:24:07.287Z