Score based diffusion models for conditional generation

Carola-Bibiane Schönlieb (U Cambridge)

Jun 02. 2022, 11:15 — 12:00

Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this talk we will introduce these models, and in particular discuss their application to learning conditional probability distributions. We discuss different estimators of the conditional score and provide a theoretical justification for one of the most successful ones. Moreover, we introduce a multi-speed diffusion framework, which leads to a new estimator for the conditional score. Our theoretical findings are accompanied by experimental results for image superresolution and image inpainting.

This is joint work with Georgios Batzolis, Christian Etmann and Jan Stanzcuk. 

Further Information
Venue:
ESI Boltzmann Lecture Hall
Recordings:
Recording
Associated Event:
Computational Uncertainty Quantification: Mathematical Foundations, Methodology & Data (Thematic Programme)
Organizer(s):
Clemens Heitzinger (TU Vienna)
Fabio Nobile (EPFL Lausanne)
Robert Scheichl (U Heidelberg)
Christoph Schwab (ETH Zürich)
Sara van de Geer (ETH Zürich)
Karen Willcox (U of Texas, Austin)