Title: Learning to predict complex outputs: a kernel view
Author: Florence D’Alché Buc (Télécom Paris)

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.