AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Infinite Gaussian Mixture Modeling with an Improved Estimation of the Number of Clusters

Avi Matza, Yuval Bistritz

AAAI 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace the baseline concentration-parameter prior with an informative inverse χ2 prior and modified Gibbs samplingIGMM · p1 syntheticestimated components (K): 23 (21) -> 6 (94)Improved
Replace the baseline concentration-parameter prior with an informative inverse χ2 prior and modified Gibbs samplingIGMM · p2 syntheticestimated components (K): 64 (38) -> 3 (84)Improved
Replace the baseline concentration-parameter prior with an informative inverse χ2 prior and modified Gibbs samplingIGMM · p3 syntheticestimated components (K): 43 (32) -> 20 (62)Improved
Replace the baseline concentration-parameter prior with an informative inverse χ2 prior and modified Gibbs samplingIGMM · p4 syntheticestimated components (K): 63 (36) -> 30 (61)Improved
Use an inverse χ2 prior for α with the modified training procedureIGMM · p1 syntheticsymmetric KL divergence: 0.027 -> 0.003Improved
Use an inverse χ2 prior for α with the modified training procedureIGMM · p2 syntheticsymmetric KL divergence: 0.082 -> 0.041Improved
Use an inverse χ2 prior for α with the modified training procedureIGMM · p3 syntheticsymmetric KL divergence: 13.37 -> 13.51Hurt
Use an inverse χ2 prior for α with the modified training procedureIGMM · p4 syntheticsymmetric KL divergence: 39.95 -> 36.28Improved
Calibrate θ roughly to the anticipated cluster-count range (ablation)Modified IGMM · p1–p4 syntheticestimated components (K): θ = 14, 16; θ = 18; θ = 20, 22, 24, 26; θ around 30 (±6); θ ranging from 12 to 22; K = 21Mixed
Replace secondary adaptive rejection sampling with closed-form posterior samplingModified IGMM · Four synthetic datasetsruntime (seconds per dataset): 996 seconds -> 223 secondsImproved
Replace the baseline IGMM training procedure with the modified IGMM procedureIGMM · Galaxyestimated components (K): 52 -> 4Improved
Replace the baseline IGMM training procedure with the modified IGMM procedureIGMM · Enzymeestimated components (K): 54 -> 5Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy