Complexity of High-Dimensional Identity Testing with Coordinate Conditional Sampling
We study the identity testing problem for high-dimensional distributions. Given as input an explicit distribution , an > 0, and access to sampling oracle(s) for a hidden distribution , the goal in identity testing is to distinguish whether the two distributions and are identical or are at le...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
ACM
2024
|
Online Access: | https://hdl.handle.net/1721.1/156665 |