Private Identity Testingfor High-Dimensional Distributions AnonymousAuthor(s) June 5, 2020

Neural Information Processing Systems 

We construct two types of testers, exhibiting tradeoffs between sample complexity and computational complexity. Finally, we provide a two-way reduction between testing a subclass of multivariate product distributions and testing univariate distributions,and thereby obtainupper and lower bounds for testingthis subclassof product distributions.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found