Clement Canonne (Stanford)Feb 4. Title and AbstractStatistical Inference Under Local Information Constraints We propose a general formulation for inference problems in this distributed setting, and instantiate it to two fundamental inference questions, learning and uniformity testing. We study the role of randomness for those questions, and obtain striking separations between public- and private-coin protocols for the latter, while showing the two settings are equally powerful for the former. (Put differently, “sharing with neighbors does help a lot for the test, but not really for learning.”) Based on joint works with Jayadev Acharya (Cornell University), Cody Freitag (Cornell University), and Himanshu Tyagi (IISc Bangalore). BioClĂ©ment L. Canonne is a Motwani Postdoctoral Fellow at Stanford University. He graduated from Columbia University in 2017, where he was advised by Rocco Servedio. His research focuses on the fields of property testing, statistics, and sublinear algorithms; specifically, on understanding the strengths and limitations of the standard models in property and distribution testing, as well as in related areas. He really likes elephants. |