Research map / Learning theory and algorithms / Clustering
Dynamic Clustering Algorithms via Small-Variance Analysis of Markov Chain Mixture Models
Trevor Campbell, Brian Kulis, Jonathan P. How
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 kernelized SD-Means instead of D-Means | D-Means · Synthetic moving rings | accuracy (%): 18.7 -> 75.1 | Improved |
| use kernelized SD-Means instead of D-Means | D-Means · Synthetic moving rings | time (s): 8.4x10^-4 -> 2.9 | Hurt |
| use SD-Means instead of D-Means | D-Means · Point cloud human segmentation | accuracy (%): 53.6 -> 86.8 | Improved |
| use SD-Means instead of D-Means | D-Means · Point cloud human segmentation | time (s): 38.1 -> 816.7 | Hurt |
| use D-Means instead of MCGMM Gibbs sampling | Gibbs · Aircraft ADS-B trajectories | accuracy (%): 36.9 -> 55.9 | Improved |
| use D-Means instead of DP-Means batch clustering | DP-Means · Aircraft ADS-B trajectories | accuracy (%): 55.6 -> 55.9 | No clear effect |
| use D-Means instead of DP-Means | DP-Means · Aircraft ADS-B trajectories | time (s): 3.1x10^3 -> 2.7x10^2 | Improved |
| use SD-Means with GP-uncertainty kernel instead of D-Means on discretized GP means | D-Means · Synthetic Gaussian processes | label accuracy: SD-Means generally outperforms D-Means | Improved |
| use SD-Means instead of D-Means | D-Means · Synthetic Gaussian processes | computation time: D-Means roughly 2 orders of magnitude faster | Hurt |
| enforce consistent cluster tracking in the accuracy metric | Gibbs and D-Means · Synthetic moving Gaussians | label accuracy: other algorithms comparable to D-Means when not enforced | Mixed |
| model cluster motion with D-Means instead of per-frame DP-Means or K-Means | K-Means and DP-Means · Sintel video color quantization | color flicker: flicker significantly reduced | Improved |
Closest papers by meaning
- Bayesian Level Set Clustering (JMLR 2026 · similarity 0.88)
- Flexible Bayesian Product Mixture Models for Vector Autoregressions (JMLR 2024 · similarity 0.87)
- Bayesian Sparse Gaussian Mixture Model for Clustering in High Dimensions (JMLR 2025 · similarity 0.87)
- Consistent Model-based Clustering using the Quasi-Bernoulli Stick-breaking Process (JMLR 2023 · similarity 0.87)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (NeurIPS 2024 · similarity 0.87)
- Global-Local Dirichlet Processes for Clustering Grouped Data in the Presence of Group-Specific Idiosyncratic Variables (ICML 2025 · 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.
