Of possible interest for someone in the SIPTA community 🙂

Yours,

Michele

Da: Siu Lun Chau <siu-lun.chau@cispa.de> Inviato: martedì 12 novembre 2024 10:53 A: researchers@lists.cispa.saarland <researchers@lists.cispa.saarland> Cc: Michele Caprio <michele.caprio@manchester.ac.uk> Oggetto: [CISPA-Researchers] Guest talk by Prof Michele Caprio (University of Manchester) on 19 Nov at 1400.

Dear CISPA Researcher,

You are cordially invited to Michele Caprio's (University of Manchester) research talk next Tuesday at 2 p.m. in D2 room 1.01. The talk is also available on Zoom [cispa-de.zoom-x.de]<https://urldefense.com/v3/__https://cispa-de.zoom-x.de/my/muandet__;!!PDiH4ENfjr2_Jw!GagvEohuJxBuU32m8RWN8UGP3RYfHsAPDF1-H-KXBxZ0Ac1VaDadD8TqGx4BcNspGHTfcKKZMLiH8hozsib6hBqhekaESN1peg$>.

Title: Optimal Transport for Epsilon Contaminated Credal Set

Talk Abstract:

We provide a version for lower probabilities of Monge's and Kantorovich's optimal transport problems. We show that, when the lower probabilities are the lower envelopes of ε-contaminated sets, then our version of Monge's, and a restricted version of our Kantorovich's problems, coincide with their respective classical versions. We also give sufficient conditions for the existence of our version of Kantorovich's optimal plan, and for the two problems to be equivalent. As a byproduct, we show that for ε-contaminations the lower probability versions of Monge's and Kantorovich's optimal transport problems need not coincide. The applications of our results to Machine Learning and Artificial Intelligence are also discussed.

Bio:

Michele is a Lecturer (Assistant Professor) in Machine Learning and Artificial Intelligence at The University of Manchester. He obtained his PhD in Statistics from Duke University, and worked as a postdoctoral researcher in the Department of Computer and Information Science of the University of Pennsylvania. His general interest is probabilistic machine learning, and in particular the use of imprecise probabilistic techniques to investigate the theory and methodology of uncertainty quantification in Machine Learning and Artificial Intelligence. Recently, he won the IJAR Young Researcher and the IMS New Researcher Awards, and he was elected a member of the London Mathematical Society.

P.S. Michele is visiting our group for a week, so if anyone is interested in learning about his amazing work on imprecise probabilistic machine learning, feel free to reach out and set up a meeting.

Best,

Siu Lun Chau

Siu Lun (Alan) Chau, Ph.D (Oxon) | Postdoctoral Researcher CISPA - Helmholtz Center for Information Security Stuhlsatzenhaus 5, 66123 Saarbrücken, +44 7415137484 | siu-lun.chau@cispa.de | https://chau999.github.io/ [chau999.github.io]<https://urldefense.com/v3/__https://chau999.github.io/__;!!PDiH4ENfjr2_Jw!GagvEohuJxBuU32m8RWN8UGP3RYfHsAPDF1-H-KXBxZ0Ac1VaDadD8TqGx4BcNspGHTfcKKZMLiH8hozsib6hBqhekZEWHIxhw$>