Speaker: Florence d'Alché-Buc (https://perso.telecom-paristech.fr/fdalche/)

Title: Learning to predict complex outputs: a kernel view

Abstract: Motivated by real-world complex output prediction tasks such as link prediction, molecule identification or functional output regression, we propose to leverage the notion of output kernel to take into account the nature of output variables whether they be discrete structures or functions. This approach boils down to encode output data as vectors of the Reproducing kernel Hilbert Space associated to the so-called output kernel. We present a vector-valued kernel machines as well as a deep variant to implement it and discuss different learning problems linked with the chosen loss function. Eventually large scale approaches can be developed using low rank approximations of the outputs. We illustrate the framework on graph prediction and infinite task learning.

Bio: Florence d'Alché-Buc is professor and head of the Image, Data and Signal department of Télécom Paris, a founding member of Institut Polytechnique de Paris (France). She was program co-chair of NeurIPS 2019 and is currently acting as action editor of Journal of Machine Learning Research and IEEE Transactions on Pattern Analysis and Machine Intelligence. She also holds the Data Science & Artificial Intelligence for Digitalized Industry & Services Chair. Her research spans many various directions in Machine Learning with non-parametric models including structured prediction, functional output regression, dynamical systems modeling and more recently, robustness and explainability.