Data Science Seminar

Learning across Incomparable Spaces (in Biomedical Applications)

Traditional machine learning tasks require a direct comparison between samples of different distributions and solely operate on data from identical metric spaces. However, one might be interested in modeling only topological or relational aspects of a distribution, either because the absolute location of the data manifold is irrelevant, e.g. distributions over spaces of learned representations, or not available, e.g. if the data is accessible only as a weighted graph among sample points. Other applications might require the use of different data sources for an analysis, e.g. different patient information need to be integrated into the algorithmic decision process. In these settings, the general principle of traditional machine learning algorithms is not satisfied and methods and distance metrics operating on incomparable spaces are required.
In this talk we discuss optimal transport, a mathematical framework for comparing probability distributions while respecting the underlying geometry and its recent success in biomedical applications. We discuss important limitations that curtail its broader applicability and introduce the Gromov-Wasserstein distance, a generalization of classic optimal transport distances to incomparable ground spaces.

Wednesday, 1st July 2020, 11 am

no video available

Biosketch Charlotte Bunne

Charlotte Bunne is a PhD student in Computer Science at Eidgenössische Technische Hochschule (ETH) Zürich under the supervision of Andreas Krause. Before, she worked with Stefanie Jegelka as a Master student at the Massachusetts Institute of Technology (MIT). During her Master’s studies in Computational Biology, she interned at IBM Research in the Computational Systems Biology Group.
Throughout her undergraduate and graduate studies, Charlotte has been Fellow of the German National Academic Foundation. For her Master’s studies Charlotte received the Excellence Scholarship of the ETH Foundation. She is a recipient of the ETH Medal.

to top
powered by webEdition CMS