Seminar series
Date
Tue, 26 May 2026
Time
12:00 -
13:00
Location
C5
Speaker
Dr. Matias Delgadino
Organisation
University of Texas at Austin
We identify the bias in the Diffusion Posterior Sampling algorithm by the use of the classical Feynman-Kac formula. This analysis, the first of its kind, allows us to understand correction/improvements to the algorithm from first principles. We show how STSL, a better performing variant of DPS, can be derived from first principles using this analysis.