Research map / Learning theory and algorithms / Sample complexity
Global Analysis of Expectation Maximization for Mixtures of Two 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 |
|---|---|---|---|
| Run Population EM from arbitrary nonzero initialization on Model 1 | Population EM · symmetric mixture of two Gaussians (Model 1) | convergence of EM iterates | Helped |
| Run Population EM on Model 2 with unknown means | Population EM · two-Gaussian mixture (Model 2) | convergence of EM iterates | Helped |
| Initialize Population EM at the zero or symmetric point | Population EM · Model 1 and Model 2 | convergence of EM iterates | Hurt |
| Run Sample-based EM from initial points where Population EM converges to truth | Sample-based EM · Gaussian mixtures | convergence of EM iterates | Helped |
| Drop the separation assumption required by prior EM analyses | EM global analysis · Gaussian mixtures | convergence of EM iterates | Helped |
Closest papers by meaning
- Benefits of over-parameterization with EM (NeurIPS 2018 · similarity 0.91)
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.88)
- Big Learning Expectation Maximization (AAAI 2024 · similarity 0.86)
- Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression (ICML 2024 · similarity 0.85)
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? (NeurIPS 2026 · similarity 0.84)
- Learning Mixtures of Experts with EM: A Mirror Descent Perspective (ICML 2025 · similarity 0.82)
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.