Approximate independence of permutation mixtures
研究了高维交换混合分布与独立同分布之间的统计距离,提出更紧的χ2散度控制方法,并由此得到新的de Finetti定理、差分隐私保证和经验贝叶斯一致性结果,适合统计、计量与隐私计算领域的学者判断是否阅读。
We prove bounds on statistical distances between high-dimensional exchangeable mixture distributions (which we call permutation mixtures) and their i.i.d. counterparts. Our results are based on a novel method for controlling χ2 divergences between exchangeable mixtures, which is tighter than the existing methods of moments or cumulants. At a technical level, a key innovation in our proofs is a new Maclaurin-type inequality for elementary symmetric polynomials of variables that sum to zero and an upper bound on permanents of doubly-stochastic positive semidefinite matrices. We obtain as a corollary a new de Finetti-style theorem (in the language of Diaconis and Freedman, 1987) as well as several new statistical results, including a differential privacy guarantee for the “shuffled privacy model” with Gaussian noise and improved generic consistency guarantees for empirical Bayes procedures in compound decision problems.