资源分类
》 资源 》论文》A Consistent Regularization Approach for Structured Prediction

A Consistent Regularization Approach for Structured Prediction

2020-02-05 | |  117 |   61 |   0

Abstract 

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We prove universal consistency and finite sample bounds characterizing the generalization properties of the proposed method. Experimental results are provided to demonstrate the practical usefulness of the proposed approach.

上一篇：Computational and Statistical Tradeoffs in Learning to Rank

下一篇：An equivalence between high dimensional Bayes optimal inference and M-estimation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...