arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.01006stat.MLcs.LG
收藏

利用可微图测试学习内隐生成模型

Learning Implicit Generative Models Using Differentiable Graph Tests

ETH Zürich(苏黎世联邦理工学院)

Josip Djolonga, Andreas Krause

摘要:

最近,人们对学习丰富的隐式模型的问题越来越感兴趣-这些模型我们可以从中采样,但不能评估其密度。这些模型将一些参数函数(例如深度网络)应用于基本度量,并且使用随机最优化进行端到端学习。设计损失函数的一个策略是通过两个样本测试的统计数据-如果我们可以欺骗统计测试,那么学习的分布应该是真实数据的良好模型。然而,并不是所有的测试都可以很容易地适应这个框架,因为它们可能无法相对于数据点进行区分,因此也无法相对于隐式模型的参数进行区分。出于这个问题,在本文中,我们将展示如何两个这样的经典测试,弗里德曼-拉夫斯基和k-最近邻测试,可以有效地平滑使用无向图形模型的思想-矩阵树定理和势。此外,正如我们的实验表明,平滑可以显着提高功率的测试,这可能是独立的利益。最后,我们应用我们的方法来学习隐式模型。

英文摘要:

Recently, there has been a growing interest in the problem of learning rich implicit models - those from which we can sample, but can not evaluate their density. These models apply some parametric function, such as a deep network, to a base measure, and are learned end-to-end using stochastic optimization. One strategy of devising a loss function is through the statistics of two sample tests - if we can fool a statistical test, the learned distribution should be a good model of the true data. However, not all tests can easily fit into this framework, as they might not be differentiable with respect to the data points, and hence with respect to the parameters of the implicit model. Motivated by this problem, in this paper we show how two such classical tests, the Friedman-Rafsky and k-nearest neighbour tests, can be effectively smoothed using ideas from undirected graphical models - the matrix tree theorem and cardinality potentials. Moreover, as we show experimentally, smoothing can significantly increase the power of the test, which might of of independent interest. Finally, we apply our method to learn implicit models.

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。

↑