Zusammenfassung für den Vortrag am 14.04.2022 (17:00 Uhr)
Math Machine Learning seminar MPI MIS + UCLAChristoph Lampert (Institute of Science and Technology, Austria)
Robust and Fair Multisource Learning
Siehe auch das Video dieses Vortrages.
In the era of big data, the training data for
machine learning models is commonly collected from multiple
sources. Some of these might not be unreliable (noisy,
corrupted, or even manipulated). Can learning algorithms
overcome this an still learn classifiers of optimal accuracy
and ideally fairness? In my talk, I highlight recent results
from our group that establish situations in which this is
possible or impossible.