Statistical Inference of Intractable Generative Models via Classification
Statistical Inference of Intractable Generative Models via Classification
复制标题
通过分类对棘手的生成模型进行统计推断
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
J. Corander
中科院分区：
文献类型：
--
作者：
Michael U Gutmann;Ritabrata Dutta;Samuel Kaski;J. Corander
越来越复杂的生成模型被用于各个学科，因为它们允许对数据进行现实的表征，但它们的一个共同困难是执行基于似然的统计推断的计算成本过高。我们在这里考虑一个无似然框架，其中推理是通过识别参数值来完成的，这些参数值产生的模拟数据与观测数据充分相似。一个主要的困难是如何测量模拟数据和观测数据之间的差异。将原始问题转化为将数据分为模拟数据和观测数据的问题，我们发现可以使用分类精度来评估差异。因此，完整的分类方法库可用于难处理生成模型的推理。
Increasingly complex generative models are being used across the disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to perform likelihood-based statistical inference. We consider here a likelihood-free framework where inference is done by identifying parameter values which generate simulated data adequately resembling the observed data. A major difficulty is how to measure the discrepancy between the simulated and observed data. Transforming the original problem into a problem of classifying the data into simulated versus observed, we find that classification accuracy can be used to assess the discrepancy. The complete arsenal of classification methods becomes thereby available for inference of intractable generative models.