Timezone: »

 
Poster
Manifold Structured Prediction
Alessandro Rudi · Carlo Ciliberto · Gian Maria Marconi · Lorenzo Rosasco

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #161
in Tue Poster Session B »

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.

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

Author Information

Alessandro Rudi (INRIA, Ecole Normale Superieure)
Carlo Ciliberto (Imperial College London)
Gian Maria Marconi (Italian Institute of Technology)
Lorenzo Rosasco (University of Genova- MIT - IIT)

More from the Same Authors