paper-with-me

Papers

Complexity of High-Dimensional Identity Testing with Coordinate Conditional Sampling

2022-07-19 · Antonio Blanca, Zongchen Chen, Daniel Štefankovič, Eric Vigoda

We study the identity testing problem for high-dimensional distributions. Given as input an explicit distribution $\mu$, an $\varepsilon>0$, and access to sampling oracle(s) for a hidden distribution $\pi$, the goal in identity testing is to distinguish whether the two distributions $\mu$ and $\pi$ are identical or are at least $\varepsilon$-far apart. When there is only access to full samples from the hidden distribution $\pi$, it is known that exponentially many samples (in the dimension) may be needed for identity testing, and hence previous works have studied identity testing with additional access to various "conditional" sampling oracles. We consider a significantly weaker conditional sampling oracle, which we call the $\mathsf{Coordinate\ Oracle}$, and provide a computational and statistical characterization of the identity testing problem in this new model. We prove that if an analytic property known as approximate tensorization of entropy holds for an $n$-dimensional visible distribution $\mu$, then there is an efficient identity testing algorithm for any hidden distribution $\pi$ using $\tilde{O}(n/\varepsilon)$ queries to the $\mathsf{Coordinate\ Oracle}$. Approximate tensorization of entropy is a pertinent condition as recent works have established it for a large class of high-dimensional distributions. We also prove a computational phase transition: for a well-studied class of $n$-dimensional distributions, specifically sparse antiferromagnetic Ising models over $\{+1,-1\}^n$, we show that in the regime where approximate tensorization of entropy fails, there is no efficient identity testing algorithm unless $\mathsf{RP}=\mathsf{NP}$. We complement our results with a matching $\Omega(n/\varepsilon)$ statistical lower bound for the sample complexity of identity testing in the $\mathsf{Coordinate\ Oracle}$ model.

📄 PDF Abstract BibTeX arXiv:2207.09102

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Private Identity Testing for High-Dimensional Distributions

2019-05-28 · NeurIPS 2020 12 · Clément L. Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman 외

In this work we present novel differentially private identity (goodness-of-fit) testers for natural and widely studied classes of multivariate product distributions: Gaussians in $\mathbb{R}^d$ with known covariance and …

Vocal Bursts Intensity Prediction

Private High-Dimensional Hypothesis Testing

2022-03-03 · Shyam Narayanan

We provide improved differentially private algorithms for identity testing of high-dimensional distributions. Specifically, for $d$-dimensional Gaussian distributions with known covariance $\Sigma$, we can test whether t…

Vocal Bursts Intensity Prediction

Testing Identity of Multidimensional Histograms

2018-04-10 · Ilias Diakonikolas, Daniel M. Kane, John Peebles

We investigate the problem of identity testing for multidimensional histogram distributions. A distribution $p: D \rightarrow \mathbb{R}_+$, where $D \subseteq \mathbb{R}^d$, is called a $k$-histogram if there exists a p…

Two-sample testing

The Sample Complexity of Robust Covariance Testing

2020-12-31 · Ilias Diakonikolas, Daniel M. Kane

We study the problem of testing the covariance matrix of a high-dimensional Gaussian in a robust setting, where the input distribution has been corrupted in Huber's contamination model. Specifically, we are given i.i.d. …

Wasserstein Identity Testing

2017-10-28 · Shichuan Deng, Wenzheng Li, Xuan Wu

Uniformity testing and the more general identity testing are well studied problems in distributional property testing. Most previous work focuses on testing under $L_1$-distance. However, when the support is very large o…