Research map / Optimization / Nonconvex and smooth optimization
High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm
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 |
|---|---|---|---|
| Replace full gradient with semi-stochastic variance-reduced gradient in gradient EM | high-dimensional gradient EM · GMM and MLR simulations | optimization error vs iterations and training time | Helped |
| Replace full gradient with semi-stochastic variance-reduced gradient in gradient EM | high-dimensional gradient EM · GMM and MLR simulations | overall estimation error | No clear effect |
| Replace regularized M-step (HDREM) with variance-reduced stochastic gradient EM | high-dimensional EM · GMM and MLR simulations | overall estimation error | Helped |
| Use stochastic variance-reduced gradient (vs full gradient) for EM M-step | high-dimensional EM · theoretical gradient complexity | gradient complexity | Helped |
| Use resampling version of the algorithm instead of Algorithm 1 in experiments | VRSGEM · theory vs practice | statistical rate | No clear effect |
Closest papers by meaning
- Stochastic Expectation Maximization with Variance Reduction (NeurIPS 2018 · similarity 0.91)
- Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models (NeurIPS 2024 · similarity 0.88)
- Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions? (NeurIPS 2026 · similarity 0.87)
- Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm (NeurIPS 2025 · similarity 0.86)
- Big Learning Expectation Maximization (AAAI 2024 · similarity 0.86)
- Heterogeneous Sufficient Dimension Reduction and Subspace Clustering (ICML 2025 · similarity 0.85)
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.