A survey on distribution testing: Your data is big. But is it blue?
CL Canonne - Theory of Computing, 2020 - theoryofcomputing.org
The field of property testing originated in work on program checking, and has evolved into
an established and very active research area. In this work, we survey the developments of …
an established and very active research area. In this work, we survey the developments of …
Optimal testing for properties of distributions
J Acharya, C Daskalakis… - Advances in Neural …, 2015 - proceedings.neurips.cc
Given samples from an unknown distribution, p, is it possible to distinguish whether p
belongs to some class of distributions C versus p being far from every distribution in C? This …
belongs to some class of distributions C versus p being far from every distribution in C? This …
Testing symmetric properties of distributions
P Valiant - Proceedings of the fortieth annual ACM symposium on …, 2008 - dl.acm.org
We introduce the notion of a Canonical Tester for a class of properties on distributions, that
is, a tester strong and general enough that" a distribution property in the class is testable if …
is, a tester strong and general enough that" a distribution property in the class is testable if …
Testing ising models
C Daskalakis, N Dikkala… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Given samples from an unknown multivariate distribution p, is it possible to distinguish
whether p is the product of its marginals versus p being far from every product distribution …
whether p is the product of its marginals versus p being far from every product distribution …
Learning and testing causal models with interventions
J Acharya, A Bhattacharyya… - Advances in …, 2018 - proceedings.neurips.cc
We consider testing and learning problems on causal Bayesian networks as defined by
Pearl (Pearl, 2009). Given a causal Bayesian network M on a graph with n discrete variables …
Pearl (Pearl, 2009). Given a causal Bayesian network M on a graph with n discrete variables …
Testing probability distributions using conditional samples
We study a new framework for property testing of probability distributions, by considering
distribution testing algorithms that have access to a conditional sampling oracle. This is an …
distribution testing algorithms that have access to a conditional sampling oracle. This is an …
Testing bayesian networks
CL Canonne, I Diakonikolas… - … on Learning Theory, 2017 - proceedings.mlr.press
This work initiates a systematic investigation of testing\em high-dimensional structured
distributions by focusing on testing\em Bayesian networks–the prototypical family of directed …
distributions by focusing on testing\em Bayesian networks–the prototypical family of directed …
Distribution testing lower bounds via reductions from communication complexity
We present a new methodology for proving distribution testing lower bounds, establishing a
connection between distribution testing and the simultaneous message passing (SMP) …
connection between distribution testing and the simultaneous message passing (SMP) …
Random restrictions of high dimensional distributions and uniformity testing with subcube conditioning
We give a nearly-optimal algorithm for testing uniformity of distributions supported on {–1, 1}
n, which makes many queries to a subcube conditional sampling oracle (Bhattacharyya and …
n, which makes many queries to a subcube conditional sampling oracle (Bhattacharyya and …
Square Hellinger subadditivity for Bayesian networks and its applications to identity testing
C Daskalakis, Q Pan - Conference on Learning Theory, 2017 - proceedings.mlr.press
We show that the square Hellinger distance between two Bayesian networks on the same
directed graph, $ G $, is subadditive with respect to the neighborhoods of $ G $. Namely, if …
directed graph, $ G $, is subadditive with respect to the neighborhoods of $ G $. Namely, if …