CS 598: Deep Generative and Dynamical Models
Spring, 2023


Course Description

Recent years have seen considerable advances in generative models, which learn distributions from data and also generate new data instances from the learned distribution; and dynamical models, which model systems with a dynamical or temporal component. Both of these developments have been leveraging advances in deep learning. The course will cover key advances in generative and dynamical models, including variational auto-encoders, normalizing flows, generative adversarial networks, diffusion models, neural differential equations, learning operators, among other topics.


Note: If you are interested in taking the class but have not managed to register because the class is full, please stay tuned.
We are exploring options to let additional students join the class.


Basic Information:

Classes: Tue, Thu 11:00 am - 12:15 pm
Location: Siebel 1302
Instructor: Arindam Banerjee, arindamb@illinois.edu
TA: Jiaqi Guan, jiaqi@illinois.edu
Office hours:
Course Syllabus Syllabus
Course Webpage: Canvas



Tentative Class Schedule

DateTopic+PapersSlidesPresenter(s)
01. Tue, Jan 17 Course Overview Overview
02. Thu, Jan 19 RBM 1: Energy Based Models, (Restricted) Boltzmann Machines (RBMs), Sigmoid Belief Networks Boltzmann Machines
03. Tue, Jan 24 RBM 2: Learning in (Restricted) Boltzmann Machines, Deep Boltzmann Machines, Contrastive Divergence Learning (R)BMs
04. Thu, Jan 26 Inf 1: Markov Chain Monte Carlo, Gibbs Sampling, Langevin Dynamics
05. Tue, Jan 31 Inf 2: Hamiltonian Monte Carlo, Variational Inference
06. Thu, Feb 2 AR 1: Neural Autoregressive Models
07. Tue, Feb 7 AR 2: PixelRNN/CNN, Quantiles
08. Thu, Feb 9 AR 3: Transformers
09. Tue, Feb 14 VAE 1: Variational Autoencoders, Evidence Lower Bound, Importance Weighting
10. Thu, Feb 16 VAE 2: Improved Inference, Information Theoretic Perspective, Representation
11. Tue, Feb 21 VAE 3: VQ VAE, Deep VAE
12. Thu, Feb 23 VAE 4: Disentanglement
13. Tue, Feb 28 DiffM1: Score Matching, Diffusion Models
14. Thu, Mar 2 DiffM2: Score Matching, Diffusion Models
15. Tue, Mar 7 DiffM3: Connections
16. Thu, Mar 9 DiffM4: Convergence, Stable Diffusion
Tue, Mar 14 Spring Break
Thu, Mar 16 Spring Break
17. Tue, Mar 21 NF 1: Normalizing Flows
18. Thu, Mar 23 NF 2: Autoregressive Flows
19. Tue, Mar 28 NF 3: Improved, Neural, Residual Flows
20. Thu, Mar 30 GAN 1: Basics, Info-GAN, f-GAN
21. Tue, Apr 4 GAN 2: DC-GAN, Cycle-GAN, Style-GAN
22. Tue, Apr 6 GAN 3: Wasserstein GANs
23. Thu, Apr 11 GAN 4: Optimization
24. Thu, Apr 13 NODE 1: Neural Ordinary Differential Equations 1
25. Tue, Apr 18 NODE 2: Neural Ordinary Differential Equations 2
26. Thu, Apr 20 LOP 1: Deep Operator Networks
27. Tue, Apr 25 LOP 2: Fourier Neural Operators
28. Thu, Apr 27
PP 1: Project Presentations 1

29. Tue, May 2
PP 2: Project Presentations 2