VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

401-4634-24L 4 Credits DR , MSC D-MATH

Computational and Statistical Aspects of Diffusion Models

Lecturers & Examiners: Prof. Dr. Yuansi Chen
VVZ CR n/a

Last Updated: 2026-06-03 00:14:18

Abstract

This is a master/PhD level course to prepare students for academic research in Markov chain Monte Carlo sampling algorithms, diffusion generative models and the associated theory. We cover basic sampling algorithms, provide geometric intuitions and demonstrate theoretical frameworks to analyze their computational and statistical performance.

Objective

The main objective is to learn about Langevin dynamics and diffusion generative models. We study their relationships from a classical point-of-view and we cover theoretical frameworks to prove computational and statistical guarantees of these sampling algorithms.

Resources

Learning Materials (Links)

General Information

Language
English
Levels
DR , MSC

Examination

Type
session examination
Mode
written 120 minutes
Aids
None

Course Components

Type Title Time & Place Hours
lecture Computational and Statistical Aspects of Diffusion Models
  • Mon 14:15-16:00 (HG E 21)
2 h weekly

Offered In