USI - Email

Archive / INF Seminars / INF_2025_05_07_Max_Pfeffer_

USI - Email

	Manifold Optimization in Data Science

Host: Prof. Michael Multerer

Wednesday

07.05

USI Lugano East Campus, Room C1.05

15:30 - 16:30


	Prof. Max Pfeffer University of Göttingen, Germany

Abstract:
Matrix and tensor factorizations are widely applied in Data Science for dimensionality and noise reduction as well as for feature extraction.
Often, additional constraints are imposed on the factors in order to improve uniqueness and interpretability of the results. We consider several specific factorization formats with smooth and nonsmooth constraints that can be computed using techniques from Riemannian optimization. For this, existing methods need to be adapted according to the problem at hand. Furthermore, we apply our methods also for Data Fusion, where several data sets are factorized simultaneously.

Biography:
Max Pfeffer completed a PhD in Mathematics at TU Berlin in 2018. From 2017 to 2020, he worked as a Postdoc with André Uschmajew at the Max Planck Institute for Mathematics in the Sciences, Leipzig. He then joined Johannes-Gutenberg-Universität Mainz as a Postdoc with Markus Bachmayr in 2020. In addition, he served as Adjunct Professor at Universität Leipzig in 2020. Following this, he held a DFG Eigene Stelle position at Technische Universität Chemnitz from 2021 to 2022, and an Adjunct Professorship there from 2022 to 2023. Since 2023, he is a Junior Professor at Georg-August-Universität Göttingen. More information can be found on his website.