Identity testing under label mismatch

05/05/2021
by   Clément L. Canonne, et al.
0

Testing whether the observed data conforms to a purported model (probability distribution) is a basic and fundamental statistical task, and one that is by now well understood. However, the standard formulation, identity testing, fails to capture many settings of interest; in this work, we focus on one such natural setting, identity testing under promise of permutation. In this setting, the unknown distribution is assumed to be equal to the purported one, up to a relabeling (permutation) of the model: however, due to a systematic error in the reporting of the data, this relabeling may not be the identity. The goal is then to test identity under this assumption: equivalently, whether this systematic labeling error led to a data distribution statistically far from the reference model.

READ FULL TEXT
research
04/27/2020

Testing Data Binnings

Motivated by the question of data quantization and "binning," we revisit...
research
04/08/2021

Unitary Subgroup Testing

We consider the problem of subgroup testing for a quantum circuit C: giv...
research
05/13/2021

Identity testing of reversible Markov chains

We consider the problem of identity testing of Markov chains based on a ...
research
07/19/2022

Identity Testing for High-Dimensional Distributions via Entropy Tensorization

We present improved algorithms and matching statistical and computationa...
research
04/05/2021

Conformal testing in a binary model situation

Conformal testing is a way of testing the IID assumption based on confor...
research
04/22/2020

Hardness of Identity Testing for Restricted Boltzmann Machines and Potts models

We study identity testing for restricted Boltzmann machines (RBMs), and ...
research
08/18/2021

Self-Sovereign Identity: A Systematic Map and Review

Self-Sovereign Identity is a user-centric identity model. In this model,...

Please sign up or login with your details

Forgot password? Click here to reset