Skip to yearly menu bar Skip to main content


Poster

Manifold Structured Prediction

Alessandro Rudi · Carlo Ciliberto · Gian Maria Marconi · Lorenzo Rosasco

Room 517 AB #161

Keywords: [ Structured Prediction ] [ Spaces of Functions and Kernels ]


Abstract:

Structured prediction provides a general framework to deal with supervised problems where the outputs have semantically rich structure. While classical approaches consider finite, albeit potentially huge, output spaces, in this paper we discuss how structured prediction can be extended to a continuous scenario. Specifically, we study a structured prediction approach to manifold-valued regression. We characterize a class of problems for which the considered approach is statistically consistent and study how geometric optimization can be used to compute the corresponding estimator. Promising experimental results on both simulated and real data complete our study.

Live content is unavailable. Log in and register to view live content