Research map / Optimization / Nonconvex and smooth optimization
On the Global Convergence of (Fast) Incremental Expectation Maximization Methods
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 |
|---|---|---|---|
| Use variance-reduced stochastic EM instead of IEM | Stochastic EM for latent-variable maximum likelihood estimation · Latent-variable maximum likelihood estimation | iterations to an ε-stationary point: O( n / ε ) -> O( n^{\frac{2}{3}} / ε ) | Helped |
| Use FIEM instead of IEM | Stochastic EM for latent-variable maximum likelihood estimation · Latent-variable maximum likelihood estimation | iterations to an ε-stationary point: O( n / ε ) -> O( n^{\frac{2}{3}} / ε ) | Helped |
| Use SEMVR or FIEM instead of the competing stochastic EM methods | Stochastic EM methods · Gaussian Mixture Models | precision convergence | Helped |
| Use FIEM or SEMVR instead of the competing EM methods | Stochastic EM methods · FAO pLSA datasets | ELBO convergence | Helped |
Closest papers by meaning
- Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression (ICML 2024 · similarity 0.87)
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.86)
- Big Learning Expectation Maximization (AAAI 2024 · similarity 0.86)
- Fearless Stochasticity in Expectation Propagation (NeurIPS 2024 · similarity 0.86)
- Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm (NeurIPS 2025 · similarity 0.85)
- EM Distillation for One-step Diffusion Models (NeurIPS 2024 · similarity 0.83)
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.