Skip to main content

Ctrl+K

Probabilistic Inference & Optimization

Probabilistic Inference & Optimization

Part I: Foundations of Inference

1. Overview: Stochastic Methods for Data Analysis
2. Maximum Likelihood Estimation
3. Bayesian Modeling
4. Bayesian versus Frequentist Inference
5. Applications and Broader Impact: Foundations of Inference

Part II: Sampling and Monte Carlo

6. Sampling for Posterior Simulation
7. Monte Carlo Integration
8. Markov Chain Monte Carlo
9. Metropolis-Hastings and Gibbs
10. Applications and Broader Impact: Sampling and Monte Carlo

Part III: Latent Variables and Variational Inference

11. Latent Variable Models and MLE
12. Bayesian Latent Variable Models and Variational Inference
13. Hierarchical Models
14. Applications and Broader Impact: Latent Variables and Variational Inference

Part IV: Optimization

15. Logistic Regression and Gradient Descent
16. Stochastic Gradient Descent and Simulated Annealing
17. Applications and Broader Impact: Optimization

Part V: Advanced MCMC

18. Hamiltonian Monte Carlo
19. Parallel Tempering and Stochastic HMC
20. Applications and Broader Impact: Advanced MCMC

Part VI: Bayesian Deep Learning

21. Neural Network Models for Regression
22. Black-box Variational Inference
23. Automatic Differentiation
24. Variational Inference in Context
25. Variational Autoencoders
26. Implementing Variational Autoencoders
27. Applications and Broader Impact: Bayesian Deep Learning

Labs

Lab 1: Review of Scientific Computing in Python
Lab 2: Posterior and Posterior Predictive Simulation
Lab 3: Sampling and Monte Carlo Integration
Lab 4: Gibbs and Metropolis-Hastings Sampling
Lab 5: KL-Divergence and Modeling with pymc3
Lab 6: Interpreting and Evaluating Logistic Regression Models
Lab 7: Non-Linear Models for Regression
Lab 8: Variational Inference vs HMC
Lab 9: Inference and Learning for Discrete-State HMMs

Repository
Open issue

Index

By Weiwei Pan

This book is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.