arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.07710stat.MLcs.LG
收藏

具有统计效率的非正态化模型的统一估计框架

Unified estimation framework for unnormalized models with statistical efficiency

Harvard University(哈佛大学);Tokyo Institute of Technology(东京工业大学);RIKEN AIP(理化学研究所人工智能研究中心);Future University Hakodate(函馆未来大学);The University of Tokyo(东京大学);RIKEN Center for Brain Science(理化学研究所脑科学中心)

Masatoshi Uehara, Takafumi Kanamori, Takashi Takenouchi, Takeru Matsuda

摘要:

非规范化模型的参数估计是一个具有挑战性的问题。这些模型的极大似然估计(MLE)在计算上是不可行的,因为归一化常数没有明确计算。虽然一些相合估计量已被提出较早,统计效率的问题仍然存在。在这项研究中,我们提出了一个统一的,统计上有效的估计框架的非正规化模型和几个有效的估计,其渐近方差是相同的极大似然估计。这些估计量的计算成本也是合理的,并且无论样本空间是离散的还是连续的,它们都可以被采用。通过结合以下两种方法推导出所提出的估计的损失函数:(1)使用Bregman散度的密度比匹配,和(2)插入非参数估计。我们还分析了所提出的估计的性质时,未规范化的模型是错误的。实验结果表明,我们的方法优于现有的方法。

英文摘要:

The parameter estimation of unnormalized models is a challenging problem. The maximum likelihood estimation (MLE) is computationally infeasible for these models since normalizing constants are not explicitly calculated. Although some consistent estimators have been proposed earlier, the problem of statistical efficiency remains. In this study, we propose a unified, statistically efficient estimation framework for unnormalized models and several efficient estimators, whose asymptotic variance is the same as the MLE. The computational cost of these estimators is also reasonable and they can be employed whether the sample space is discrete or continuous. The loss functions of the proposed estimators are derived by combining the following two methods: (1) density-ratio matching using Bregman divergence, and (2) plugging-in nonparametric estimators. We also analyze the properties of the proposed estimators when the unnormalized models are misspecified. The experimental results demonstrate the advantages of our method over existing approaches.

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。

↑