Mar 5 – 6, 2026
CERN
Europe/Berlin timezone

An IRIS-HEP Blueprint Workshop

Differentiating Discrete Operations [10' + 5']

Mar 5, 2026, 2:55 PM
15m
4/3-006 - TH Conference Room (CERN)

4/3-006 - TH Conference Room

CERN

110
Show room on map

Speaker

Annalena Kofler (Technical University Munich)

Description

Discrete decisions arise in simulators and analysis pipelines across disciplines such as biophysics, robotics, and HEP. Because these operations are inherently non-differentiable, the machine learning community has developed a range of methods to obtain such gradients. In this talk, I outline why a statistical perspective on gradient estimation is essential in this setting and give a brief overview of existing approaches for handling discrete decisions.

Presentation materials