Kernel mean embedding is a useful tool to represent and compare probability measures. Despite its usefulness, kernel mean embedding considers infinite-dimensional features, which are challenging to handle in the context of differentially private data generation. A recent work proposes to approximate the kernel mean embedding of data distribution using finite-dimensional random features, which yields analytically tractable sensitivity. However, the number of required random features is excessively high, often ten thousand to a hundred thousand, which worsens the privacy-accuracy trade-off. To improve the trade-off, we propose to replace random features with Hermite polynomial features. Unlike the random features, the Hermite polynomial features are ordered, where the features at the low orders contain more information on the distribution than those at the high orders. Hence, a relatively low order of Hermite polynomial features can more accurately approximate the mean embedding of the data distribution compared to a significantly higher number of random features. As demonstrated on several tabular and image datasets, Hermite polynomial features seem better suited for private data generation than random Fourier features.
翻译:内核嵌入是代表并比较概率度量的有用工具。 尽管内核嵌入是一种有用的工具, 内核意味着考虑无限的尺寸特征, 这些特征在不同的私人数据生成中处理是困难的。 最近的一项工作建议使用有限维随机特性来估计数据分布的内核意味着嵌入内核, 从而产生可分析的敏感度。 但是, 所需的随机特性数量太高, 通常为一万至十万个, 使隐私- 准确性交易更加恶化。 为改善权衡, 我们提议用Hermite 多边名词取代随机特性。 与随机特性不同, Hermite 多元名词是定的, 低排序的特性含有关于数据分布的信息比高排序的特性要多。 因此, Hermite 多元海洋特征的相对较低顺序可以更准确地估计数据分布的内嵌入平均值, 而随机特性则要高得多。 正如几个表格和图像数据集所显示的那样, Hermite 多边名特征似乎更适合私人数据生成的私人数据, 而不是随机四等特性。