arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1805.08196cs.LGstat.ML
收藏

多项式时间结构预测的学习最大后验扰动模型

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

Purdue University(普渡大学)

Asish Ghoshal, Jean Honorio

摘要:

MAP扰动模型已经成为结构化预测中推理的一个强大框架。这种模型提供了一种有效地从吉布斯分布中采样的方法,并有助于对随机噪声具有鲁棒性的预测。在本文中,我们提出了一个可证明的多项式时间随机算法学习参数的扰动MAP预测。我们的方法是基于最小化一个新的Rademacher为基础的泛化上的扰动MAP预测,这可以在多项式时间计算的预期损失的界限。我们获得的条件下,我们的随机学习算法可以保证推广到看不见的例子。

英文摘要:

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 perturbed MAP predictor, which can be computed in polynomial time. We obtain conditions under which our randomized learning algorithm can guarantee generalization to unseen examples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑