Testing Probability Distributions Underlying Aggregated Data
In this paper, we analyze and study a hybrid model for testing and learning probability distributions. Here, in addition to samples, the testing algorithm is provided with one of two different types of oracles to the unknown distribution D over [n]. More precisely, we consider both the dual and cumu...
Main Authors: | Canonne, Clement (Author), Rubinfeld, Ronitt (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Springer-Verlag,
2016-01-27T16:55:34Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Testing Shape Restrictions of Discrete Distributions
by: Canonne, Clément L., et al.
Published: (2017) -
Monotone probability distributions over the Boolean cube can be learned with sublinear samples
by: Rubinfeld, Ronitt, et al.
Published: (2021) -
Property Testing and Probability Distributions: New Techniques, New Models, and New Goals
by: Canonne, Clement Louis
Published: (2017) -
Sampling correctors
by: Canonne, Clement L, et al.
Published: (2017) -
Testing non-uniform k-wise independent distributions over product spaces (extended abstract)
by: Rubinfeld, Ronitt, et al.
Published: (2012)