Introduction to adversarially robust learning

21.05.2024 14:00 - 14:20

Daniel Bartl (University of Vienna)

Abstract: In this short lecture, we will explain the fundamental principles of robust learning, i.e. learning from possibly contaminated data. Our emphasis will be on statistical considerations and we illustrate the concepts using a simple example: estimating the location parameter of a Gaussian random variable from a sample that may be contaminated.

Zoom-Link:
https://univienna.zoom.us/j/63667270827?pwd=Rkg2ODdqeTBtQTMwNWFYdVo3by9KZz09

 

 

 

 


Organiser:

Fakultät für Mathematik, Dekan Radu Ioan Boţ

Location:

BZ 2, 2. OG., OMP 1