资源分类
》 资源 》论文》Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time

Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time

2020-03-20 | |  54 |   43 |   0

Abstract

MAP perturbation models have emerged as a powerful framework for inference in structured prediction. Such models provide a way to efficiently sample from the Gibbs distribution and facilitate predictions that are robust to random noise. In this paper, we propose a provably polynomial time randomized algorithm for learning the parameters of perturbed MAP predictors. Our approach is based on minimizing a novel Rademacher-based generalization bound on the expected loss of a per turbed MAP predictor, which can be computed in polynomial time. We obtain conditions under which our randomized learning algorithm can guarantee generalization to unseen examples.

上一篇：Rapid Adaptation with Conditionally Shifted Neurons

下一篇：Detecting non-causal artifacts in multivariate linear regression models

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

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

  • Rating-Boosted La...

    The performance of a recommendation system reli...