Please join us on Wednesday, December 3, 2025 for the Pierce Seminar at 4:15 PM in Room 3-270 with Prof. Dario Paccagnan (Imperial College London). Refreshments to be served at 4:00 PM. 

Abstract Title: Pick To Learn: State-Of-The-Art Safety Guarantees For Machine Learning And Robotics

Abstract: 

AI models are increasingly embedded in scientific research and industrial production, where they inform predictions and drive decisions. Yet, in safety-critical settings including autonomous driving and robotics, deploying these models requires rigorous safety and performance guarantees — a need that has motivated much recent work at the interface of statistical learning and control. However, existing approaches, including conformal prediction, test-set methods, and PAC-Bayes bounds, face two major limitations: they either require setting aside part of the dataset to generate guarantees — possibly degrading the quality of the learned model —  or they produce bounds that often do not reflect true performance.

In this talk, I will present a recent line of work that overcomes these limitations by enabling the use of all available data to jointly train models and equip them with tight safety or performance guarantees. The core technical idea is to embed any black-box learner into a suitably constructed meta-algorithm, Pick-to-Learn, which turns the original black-box algorithm into a sample compression scheme from which sharp guarantees can be derived.

I will then show how, across a breadth of applications in machine learning and robotics, Pick To Learn delivers both better-performing models and tighter certificates than the state of the art, highlighting its potential for broad practical impact. 

Bio:

Dario Paccagnan is an Associate Professor at the Department of Computing, Imperial College London where he joined in the Fall 2020. Before that, he was a postdoctoral fellow at the University of California, Santa Barbara. He obtained his PhD from the Automatic Control Laboratory, ETH Zurich, Switzerland, in 2018. He received a B.Sc. and M.Sc. in Aerospace Engineering from the University of Padova, Italy, in 2011 and 2014, and a M.Sc. in Mathematical Modelling and Computation from the Technical University of Denmark in 2014; all with Honors. Dario's interests are at the interface of game theory, control theory, and learning theory with a focus on tackling societal-scale challenges. He was a finalist for the 2019 EECI best PhD thesis award and was recognized with the SNSF Early Postdoc Mobility Fellowship, the SNSF Doc Mobility Fellowship, and the ETH medal for his doctoral work. He is the recipient of the best student paper award (as advisor) at AISTAT 2025.