Generative Modeling Summer School

Eindhoven, June 24th to 28th, 2024

DTU Logo TUE logo Inria Logo

About

The summer school is targeted toward PhD students working with data science and/or AI broadly, and for whom generative modeling potentially plays a part in their projects. In particular, the program is designed to accommodate both students doing methodological data science research (e.g., machine learning, statistics, and AI) and students doing applied data science research (e.g., bioinformatics, computational physics, computational chemistry, and computational social science). Furthermore, the course will also be open to postdocs and more senior researchers from the industry as continual training in AI.

Program

Monday (Jun 24) Tuesday (Jun 25) Wednesday (Jun 26) Thursday (Jun 27) Friday (Jun 28)
Day 1
Lectures & Hands-on
Day 2
Lectures & Hands-on
Day 3
Lectures & Poster session
Day 4
Invited Lectures & Dinner
Day 5
Invited Lectures
9:00-9:15
Opening remarks
Registration from 8:45
Jakub Tomczak


9:15-10:30
Introduction to generative modeling
Pierre-Alexandre Mattei
9:30-10:30
Autoregressive models (Introduction)
Jakub Tomczak
9:30-10:30
Hybrid modeling
Jakub Tomczak
09:00-10:30
Invited lecturer
Lecture title
09:00-10:30
Invited lecturer
Lecture title
11:00-12:00
From Mixture Models to Probabilistic circuits
Jakub Tomczak
11:00-12:00
Autoregressive models (Transformers)
Jakub Tomczak
11:00-12:00
Energy-based models
Jes Frellsen
11:00-12:30
Invited lecturer
Lecture title
11:00-12:30
Invited lecturer
Lecture title
12:00-13:30
Lunch
12:00-13:30
Lunch
12:00-13:30
Lunch
12:30-14:00
Lunch
12:30-14:00
Lunch
13:30-14:30
Probabilistic PCA
Pierre-Alexandre Mattei
13:30-15:00
Flow-based models
Jes Frellsen
13:30-15:00
Diffusion-based generative models
Jakub Tomczak
14:00-15:30
Invited lecturer
Lecture title
14:00-15:30
Invited lecturer
Lecture title
14:45-16:15
Deep latent variable models
Jes Frellsen
15:15-16:00
Flow-based models in VAEs
Jes Frellsen
15:15-16:00
Generative Adversarial Networks
Pierre-Alexandre Mattei
16:00-17:30
Invited lecturer
Lecture title
16:00-16.30
Closing
Jakub Tomczak
16:30-18:00
Hands-on session
VAE
16:30-18:00
Hands-on session
ARM/Flows
17:00-19:00
Poster session
19:00-21:00
Banquet dinner

Venue

The Summer School will be hosted at the Eindhoven University of Technology (TU/e) (Eindhoven, the Netherlands).

The TU/e campus is at the heart of Brainport, Europe’s most innovative technology region. The region is known for its innovative strength and multi-disciplinary way of working. Companies and organizations excel at inventing, developing and integrating the world’s most complex high-tech machines, systems, components and products with utmost precision and unprecedented accuracy. Our university campus is located near the train station and the city centre, a half-hour drive from the Eindhoven Airport and a 5 min walking distance from the train station (Eindhoven Centraal).

More information how to get to the campus could be found here.

Details about specific rooms will be announced later.

GeMSS as a Course

GeMSS could be treated as a PhD course worth ECTS (the amount of the points depends on university's guidelines). After attending the summer school, a certificate of the attendence and the accomplishment could be provided.

In order to obtain an official certificate, a participant must fulfill the following components (all components will be graded pass/fail):

  • attending the lectures;
  • accomplishing both assignments;
  • presenting a poster.

NOTE: All non-PhD-student participants will obtain a certificate of the course accomplishment/attendence as well.

Course material

Most of the material presented during the first three days of the summer school is based on the book Deep Generative Modeling (2022) by Jakub Tomczak. We highly suggest starting reading the relevant chapters before the summer school. Moreover, in the assignments (the Colab notebooks, which will be shared before the summer school), we provide the recommended reading for each assignment.

Submission & Registration

Application

Please prepare a single PDF file that contains the following information in the given order:

  • one A4 page describing your research, preferably in a poster format;
  • a one-page CV;
  • students only: a one-page letter of confirmation that you are a PhD student from your supervisor;

Please upload this single file to the following submission system (please create a submission, do not register yet).

An example of an application could be found here: [PDF].

Application deadline: April 3, 2024 (23:59 Central European Summer Time).

Selection Process

We aim for selecting a group of about 130 participants (the max. capacity of lecture rooms). The selection process will be based on the submitted material and will be executed by the organisers. We will look into your background (e.g., expertise, relevance) and your experience. We expect from the participants the following: a good familiarity with Python and PyTorch, and a basic knowledge of calculus, linear algebra, probability theory and statistics.

Registration Fee

  • PhD students: 400EUR
  • Industrial applicants: 800EUR

The registration fee includes participating in all lectures, coffee breaks, lunches and the banquet. All other costs not specified in the previous sentence (e.g., accomodation, travels, communication, other meals) are NOT provided by the organisers.

IMPORTANT!
After the selection for the summer school, you are obliged to pay the registration fee to:
the following registration system.