Stochastic Block Models with R: Statistically rigorous clustering

on YouTube ↗24m

" summary

Native R package SBMR fits Poisson stochastic block models for (bi)partite graphs using Rcpp, runs agglomerative merging with a delta ratio heuristic to pick k, then performs MCMC sweeps that use a track pairs tally to build a consensus matrix. On a simulated dense network of three clusters with 40 nodes each the pipeline perfectly recovers the true blocks, and visualizations include a consensus embedding called consensus sne to show cluster stability and node‑level uncertainty.

AI-written summary · about

" chapters (19)

1. 0:00Intro
2. 0:30Stochastic Block Models with R: er Statistically rigerous clusting with rigorous code
3. 1:03About Me
4. 2:27Bi or Poly-partite networks
5. 3:03The Stochastic Block Model? A network model to clusterodes into blocks
6. 3:40An equation for validity
7. 8:34Tests and simulated data catch errors Software Unit Tests
8. 10:20Getting speedy with it
9. 11:34Documentation as tests
10. 12:45Vignette or perish
11. 13:45What exactly is sbmR?
12. 14:40What is needed to use it?
13. 16:55Simulate a network
14. 17:56Find optimal MCMC initialization
15. 19:41Sanity check... We can join the models state after our collapse with the true generating data's blocks to see how wel
16. 20:17Sampling from posterior
17. 21:13Investigating Uncertainty in clustering
18. 22:08Concensus-SNE
19. 22:54Future plans

" related talks

• 45mCorrelated Stochastic Block Models: Graph Matching And Community RecoveryMiklos Racz · Algorithmic Advances for Statistical Inference with Combinatorial Structure
• 25mLucky Talk: From Coding to ClusteringEmmanuel Abbe · Information Theory, Learning and Big Data (Simons Institute, 2015)
• 38mBias-Adjusted Spectral Clustering In Multi-Layer Stochastic Block ModelsJing Lei · Statistics in the Big Data Era 2022
• 01h 27mFlexible Statistical ModelingChris Fonnesbeck · PyData London 2026
• 54mNode Privacy, High-dimensional Graph Summaries, and Block ModelsAdam M. Smith · Privacy and the Science of Data Analysis 2019
• 25mFundamental Limit of Community Detection in Stochastic Block ModelsEmmanuel Abbe · Information Theory, Learning and Big Data (Simons Institute, 2015)
• 41mBayesian Network Modeling using R and PythonPragyansmita Nayak · PyData DC 2016
• 01h 06mNonparametric Bayesian Methods: Models, Algorithms, and Applications ITamara Broderick · Foundations of Machine Learning Boot Camp 2017