Week 6

Lecture

• Lecture #10: Bayesian Latent Variable Models and Variational Inference
  • Lecture Video
  • Lecture Notes
• Lecture #11: Hierarchical Models
  • Lecture Video
  • Lecture Notes
  • Lecture Summary

Activities

• In-Class Exercise #10: Variational Inference
• In-Class Exercise #11: Properties of the KL-Divergence
• In-Class Exercise #11: Solutions
• Homework #5
• Homework #5 Solutions

Reading

Applications and Broader Impact

1. We Don’t Have Enough Women in Clinical Trials — Why That’s a Problem
2. Why Are Health Studies So White?
3. Characterizing the Uncertainty of Climate Change Projections Using Hierarchical Models
4. Groove Radio: A Bayesian Hierarchical Model for Personalized Playlist Generation
5. Replication of Breast Cancer Susceptibility Loci in Whites and African Americans Using a Bayesian Approach

Variational Inference

1. (Introductory) Coordinate Ascent Mean-field Variational Inference (Univariate Gaussian Example)
2. (In-Depth) Variational Inference: A Review for Statisticians
3. (Introductory) Kullback-Leibler divergence
4. (Advanced) Shannon Entropy and Kullback-Leibler Divergence

Hierarchical Bayes and Model Selection

1. (Introductory) Visual explanation for why we do hierarchical modeling
2. (In-Depth) Introduction to Hierarchical Models
3. (Introductory) Taming False Discoveries with Empirical Bayes
4. (Introductory) Bayesian Model Selection 
5. (Advanced) Model Selection with AIC, BIC etc
6. (In-Depth) Understanding predictive information criteria for Bayesian models

pymc3

1. (Introductory) Getting started with pymc3 
2. (Tutorials) pymc3 Tutorials