We demonstrate that Least Squares EM, a variant of the EM algorithm, converges to the true location parameter from a randomly initialized point.

This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities. We demonstrate that Least Squares EM, ...

Jun 16, 2019 · This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities.

This paper analyzes least square EM for mixture of two log concave distributions (that are rotationally invariant) and proves global convergence.

It is demonstrated that Least Squares EM, a variant of the EM algorithm, converges to the true location parameter from a randomly initialized point, ...

Jun 19, 2019 · In this paper, we have established the global convergence of the Least Squares EM algorithm for a mixture of two log-concave densities. The ...

This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities. We demonstrate that Least Squares EM, ...

NueralPS 2019 paper: "Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities". 0 stars 0 forks Branches Tags Activity.

This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities. We demonstrate that Least Squares EM, ...

Author(s) / Creator(s):: Qian, Wei; Zhang, Yuqian; Chen, Yudong ; Date Published: 2019-01-01 ; Journal Name: Neural Information Processing Systems Conference.