Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Sparse Gaussian Mixture Model for Clustering in High Dimensions
Dapeng Yao, Fangzheng Xie, Yanxun Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Bayesian sparse GMM instead of PCA-KM, MClust, SKM, CHIME | Bayesian sparse GMM · Scenario I (K*=3, s=6) | ARI: 0.84 vs 0.54 (PCA-KM) | Improved |
| increase support size s from 6 to 12 (ablation) | Bayesian sparse GMM · Scenario I (K*=3) | ARI: 0.84 -> 0.98 | Improved |
| increase support size s from 6 to 12 (ablation) | Bayesian sparse GMM · Scenario I (K*=5) | ARI: 0.94 -> 0.99 | Improved |
| adaptive estimation of K (Bayesian) instead of silhouette/BIC selection | Scenario I K*=3 · Scenario I (K*=3, s=12) | replicates with correct K: 98 of 100 replicates vs all competitors estimating 2 clusters | Improved |
| use Bayesian method in presence of a tiny cluster | Bayesian sparse GMM · Scenario II (small cluster) | correct K: K = 3 in 96 out of 100 replicates; competitors K = 2 in all 100 | Improved |
| fix K to truth for competitors in Scenario II | SKM, PCA-KM, MClust · Scenario II (small cluster, K fixed to 3) | ARI: 0.76, 0.84, 0.79 vs 0.99 for Bayesian | Hurt |
| Gaussian working likelihood under multivariate t data (misspecification) | Bayesian sparse GMM · Scenario III | ARI: average ARI of 0.97; K=3 in 76 of 100 replicates | No clear effect |
| Gaussian MClust/CHIME under t misspecification | MClust, CHIME · Scenario III | ARI: only one cluster in 93 out of 100 replicates, ARI less than 0.05 | Hurt |
| Bayesian method vs K-means variants on real scRNA-Seq | Bayesian sparse GMM · scRNA-Seq | ARI: 0.84 vs 0.79 (KM) | Improved |
| Bayesian method vs SKM on scRNA-Seq | Bayesian sparse GMM · scRNA-Seq | NMI: 0.80 vs 0.22 (SKM) | Improved |
Closest papers by meaning
- Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap (NeurIPS 2022 · similarity 0.90)
- Sketching in High-Dimensional Regression With Big Data Using Gaussian Scale Mixture Priors (JMLR 2025 · similarity 0.88)
- Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models (TPAMI 2018 · similarity 0.87)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.87)
- Bayesian Covariate-Dependent Gaussian Graphical Models with Varying Structure (JMLR 2022 · similarity 0.87)
- Learning Mixtures of Gaussian Processes through Random Projection (ICML 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.
