Research map / Learning theory and algorithms / Matrix and tensor methods
Convergence of Gradient EM on Multi-component Mixture of Gaussians
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase cluster weight imbalance kappa = pi_max/pi_min | Gradient EM on GMM · synthetic 3-component 2D GMM | local convergence rate | Hurt |
| increase signal-to-noise ratio (Rmin) from 1 to 5 | Gradient EM on GMM · synthetic 3-component 2D GMM | convergence rate | Helped |
| initialize gradient EM close to boundary of contraction region (shrinking epsilon) | Gradient EM · synthetic 3-component 2D GMM | convergence to true centers | No clear effect |
| initialize two centers at midpoints between true centers (a = Rmin/2) | Gradient EM · synthetic 3-component 2D GMM | convergence to global optimum | Hurt |
Closest papers by meaning
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.95)
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? (NeurIPS 2026 · similarity 0.92)
- Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences (NeurIPS 2016 · similarity 0.90)
- Big Learning Expectation Maximization (AAAI 2024 · similarity 0.88)
- Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters (NeurIPS 2026 · similarity 0.87)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.