TY - GEN UR - https://papers.nips.cc/paper/2018/hash/f6185f0ef02dcaec414a3171cd01c697-Abstract.html PB - Neural Information Processing Systems (NIPS) N2 - 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 ID - discovery10118772 A1 - Rudi, A A1 - Ciliberto, C A1 - Marconi, GM A1 - Rosasco, L T3 - Advances in Neural Information Processing Systems CY - Montreal, Canada Y1 - 2018/12/08/ AV - public EP - 12 TI - Manifold Structured Prediction N1 - This version is the version of record. For information on re-use, please refer to the publisher?s terms and conditions. ER -