Jingyi Gao
Jingyi Gao has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Christopher Ye
University of California San Diego
1 shared publication - Daniel M. Kane
University of Wisconsin-Madison University of California San Diego
1 shared publication - Ilias Diakonikolas
University of Wisconsin-Madison University of California San Diego
1 shared publication Sihan Liu
1 shared publication
Latest Publications
- Open Access
Replicable Distribution Testing
We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample complexity of replicably testing natural properties of the underlying distributions. On the algorithmic front, we develop new replicable algorithms for testing closeness and independence of discrete distributions. On the lower bound front, we develop a new methodology for proving sample complexity lower bounds for replicable testing that may be of broader interest. As an application of our technique, we establish near-optimal sample complexity lower bounds for replicable uniformity testing -- answering an open question from prior work -- and closeness testing.
Open AccessReplicable Distribution Testing
We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample complexity of replicably testing natural properties of the underlying distributions. On the algorithmic front, we develop new replicable algorithms for testing closeness and independence of discrete distributions. On the lower bound front, we develop a new methodology for proving sample complexity lower bounds for replicable testing that may be of broader interest. As an application of our technique, we establish near-optimal sample complexity lower bounds for replicable uniformity testing -- answering an open question from prior work -- and closeness testing.