Schedule
Date  Lecture  Readings  Logistics  

Module 1: Introduction, Representation, and Exact Inference  
1/14 
Lecture #1
(Eric):
Introduction to GM [ slides (annotated)  video  notes ] 


1/16 
Lecture #2
(Eric):
Representation: Directed GMs (BNs) [ slides (annotated)  video  notes ] 

1/21  No class (MLK day)  
1/23 
Lecture #3
(Eric):
Representation: Undirected GMs (MRFs) [ slides (annotated)  video  notes ] 


1/28 
Lecture #4
(Eric):
Exact inference  Elimination  Message passing  Sum product algorithm [ slides (annotated)  video  notes ] 

HW1 out (Mon, 1/28) 

1/30 
Lecture #5
(skipped):
Parameter learning in fully observable Bayesian Networks  Generalized Linear Models (GLIMs)  Maximum Likelihood Estimation (MLE)  Markov Models [ slides  video  notes ] 


2/4 
Lecture #6
(Maruan):
Parameter Learning of partially observed BN  Mixture models  Hidden Markov Models (HMMs)  The EM algorithm [ slides  video  notes ] 


2/6 
Lecture #7
(Eric):
Maximum likelihood learning of undirected GM [ slides (annotated)  video  notes ] 


2/11 
Lecture #8
(guest lecture, Kun Zhang @ Department of Philosophy):
Causal discovery and inference [ slides  video  notes ] 


2/13 
Lecture #9
(Eric):
Modeling networks  Gaussian graphical models  Ising models [ slides (annotated)  video  notes ] 

HW1 due (Wed, 2/13) 

2/18 
Lecture #10
(Eric):
Sequential models  Discrete Hidden State (HMM vs. CRF)  Continuous Hidden State (Kalman Filter) [ slides (annotated)  video  notes ] 


Module 2: Approximate Inference  
2/20 
Lecture #11
(Eric):
Approximate Inference: Mean Field (MF) and loopy Belief Propagation (BP) approximations [ slides (annotated)  video  notes ] 
HW2 out (Fri, 2/22) 

2/25 
Lecture #12
(Eric):
Theory of Variational Inference: Inner and Outer Approximations [ slides (annotated)  video  notes ] 


2/27 
Lecture #13
(Eric):
Approximate Inference: Monte Carlo and Sequential Monte Carlo methods [ slides (annotated)  video  notes ] 


3/4 
Lecture #14
(Eric):
Markov Chain Monte Carlo  MetropolisHastings  Hamiltonian Monte Carlo  Langevin Dynamics [ slides (annotated)  video  notes ] 


Module 3: Deep Learning & Generative Models  
3/6 
Lecture #15
(Eric):
Statistical and Algorithmic Foundations of Deep Learning  Insight into DL  Connections to GM [ slides  video  notes ] 

HW2 due (Mon, 3/11) 

3/11  No classes (Spring break)  
3/13  No classes (Spring break)  
3/18 
Lecture #16
(guest lecture, Zhiting Hu):
Building blocks of DL  RNN and LSTM  CNN, Transformers  Attention mechanisms  (Case studies in NLP) [ slides  video  notes ] 

HW3 out (Mon, 3/18) 

3/20 
Lecture #17
(Eric):
Deep generative models (part 1): Overview of advances and theoretical basis of deep generative models  Wake sleep algorithm  Variational autoencoders  Generative adversarial networks [ slides  video  notes ] 

3/25 
Lecture #18
(guest lecture, Zhiting Hu):
Deep generative models (part 2)  Variational Autoencoders (VAE)  Normalizing Flows  Inverse Autoregressive Flows  GANs and Implicit Models [ slides  video  notes ] 

3/27 
Lecture #19
(guest lecture, Zhiting Hu):
A unified view of deep generative models  New formulations of deep generative models  Symmetric modeling of latent and visible variables  Evaluation of Deep Generative Models [ slides  video  notes ] 
Midway report due (Fri, 3/29) 

Module 4: Reinforcement Learning & Control Through Inference in GM  
4/1 
Lecture #20
(Maruan):
Sequential decision making (part 1): The framework  Brief introduction to reinforcement learning (RL)  Connections to GM: RL and control as inference [ slides  video  notes ] 

4/3 
Lecture #21
(Maruan):
Sequential decision making (part 2): The algorithms  Maximum entropy RL and inverse RL  Maxentropy policy gradient algorithms  Soft Qlearning algorithms  Some open questions/challenges  Applications/case studies (games, robotics, etc.) [ slides  video  notes ] 
HW3 due (Wed, 4/3) 

Module 5: Nonparametric methods  
4/8 
Lecture #22
(Eric):
Bayesian nonparameterics  Dirichlet process (DP)  Hierarchical Dirichlet Process (HDP)  Chinese Restaurant Process (CRP)  Indian Buffet Process (IBP) [ slides  video  notes ] 
HW4 out (Mon, 4/8) 

4/10 
Lecture #23
(Maruan):
Gaussian processes (GPs) and elements of metalearning  GPs and (deep) kernel learning  Metalearning formulation as learning a process  Hypernetworks and contextual networks  Neural processes (NPs) as an approximation to GPs [ slides  video  notes ] 

4/15 
Lecture #24
(Eric):
Regularized Bayesian GMs (structured sparsiry, diversity, etc.) [ slides  video  notes ] 

4/17 
Lecture #25
(Eric):
Elements of Spectral & Kernel GMs [ slides  video  notes ] 

Module 6: Modular and scalable algorithms and systems  
4/22 
Lecture #26
:
Automated blackbox variational inference and elements of probabilistic programming [ slides  video  notes ] 
HW4 due (Mon, 4/22) 

4/24 
Lecture #27
(Eric):
Scalable algorithms and systems for learning, inference, and prediction [ slides  video  notes ] 

4/29 
Lecture #28
(Eric):
Industialization of AI: standards, modules, buildingblocks, and platform [ slides  video  notes ] 

5/1  Project presentations (TBA) 