English

Manifold Optimization for Gaussian Mixture Models

Machine Learning 2015-06-26 v1 Machine Learning Optimization and Control

Abstract

We take a new look at parameter estimation for Gaussian Mixture Models (GMMs). In particular, we propose using \emph{Riemannian manifold optimization} as a powerful counterpart to Expectation Maximization (EM). An out-of-the-box invocation of manifold optimization, however, fails spectacularly: it converges to the same solution but vastly slower. Driven by intuition from manifold convexity, we then propose a reparamerization that has remarkable empirical consequences. It makes manifold optimization not only match EM---a highly encouraging result in itself given the poor record nonlinear programming methods have had against EM so far---but also outperform EM in many practical settings, while displaying much less variability in running times. We further highlight the strengths of manifold optimization by developing a somewhat tuned manifold LBFGS method that proves even more competitive and reliable than existing manifold optimization tools. We hope that our results encourage a wider consideration of manifold optimization for parameter estimation problems.

Keywords

Cite

@article{arxiv.1506.07677,
  title  = {Manifold Optimization for Gaussian Mixture Models},
  author = {Reshad Hosseini and Suvrit Sra},
  journal= {arXiv preprint arXiv:1506.07677},
  year   = {2015}
}

Comments

19 pages

R2 v1 2026-06-22T10:00:01.982Z