18
Mar
©geralt - pixabay.com
Lecture
Leveraging Predictive Uncertainty to Enable Reliable Deployment of AI Models
Florian Buettner, Goethe-University Frankfurt
18.03.2025
10:30 am - 11:30 am
LMU Munich, Ludwigstr. 28 VG/II; Room 211b
This talk explores a unified theoretical framework for uncertainty quantification in machine learning, extending traditional methods to modern applications like generative modeling. By generalizing the bias-variance decomposition using proper scores, it introduces Bregman Information as a key component for epistemic uncertainty estimation. The session also covers uncertainty calibration, highlighting relationships between different calibration metrics. Finally, a novel approach for uncertainty-aware performance monitoring is presented, improving reliability under distribution shifts through active labeling interventions.
Organized by:
LMU Munich School of Management
Related
Munich AI Lectures • 09.07.2025 • Plenarsaal of the Bavarian Academy of Sciences and Humanities (BAdW), Alfons-Goppel-Straße 11, 80539 Munich
Foundational Methods for Foundation Models for Scientific Machine Learning
The Munich AI Lectures on July 9th, 2025, will feature Virginia Dignum and focus on responsible AI and foundational methods for SciML models.
©voxel51
Meetup • 09.07.2025 • Online
The Best of CVPR 2025 Series
Voxel51’s “Best of CVPR” event features top 2025 computer vision research, including Cecilia Curreli presenting on human motion prediction.
©1E9
Festival • 03.07.2025 - 06.07.2025 • Deutsches Museum, Munich
Festival of the Future 2025
Festival of the Future 2025 takes place from July 3 to 6, 2025, covering AI, sustainability, and space, with Björn Ommer as a speaker.
©Feel-good-studio-stock-adobe.com
Lecture • 26.06.2025 • CAS, Seestraße 13, 80802 Munich
Bayesian Insights on Polarization and Disagreement
As part of the CAS Research Focus, Leah Henderson explores societal polarization using Bayesian models, offering insights on handling disagreements.