method · first seen 6 Oct 2026
gradient expectation-maximization
Also: gradient EM
A variant of the EM algorithm that performs gradient-based updates on component parameters of latent variable models.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?Papers · 6 Oct 2026 · Yiran Zhang, Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du
Latest sources
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?Papers · 6 Oct 2026 · Yiran Zhang, Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du