Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887289949> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2887289949 startingPage "133" @default.
- W2887289949 abstract "We study the problem of testing identity against a given distribution (a.k.a. goodness-of-fit) with a focus on the high confidence regime. More precisely, given samples from an unknown distribution $p$ over $n$ elements, an explicitly given distribution $q$, and parameters $0< epsilon, delta < 1$, we wish to distinguish, with probability at least $1-delta$, whether the distributions are identical versus $epsilon$-far in total variation (or statistical) distance. Existing work has focused on the constant confidence regime, i.e., the case that $delta = Omega(1)$, for which the sample complexity of identity testing is known to be $Theta(sqrt{n}/epsilon^2)$. Typical applications of distribution property testing require small values of the confidence parameter $delta$ (which correspond to small $p$-values in the statistical hypothesis testing terminology). Prior work achieved arbitrarily small values of $delta$ via black-box amplification, which multiplies the required number of samples by $Theta(log(1/delta))$. We show that this upper bound is suboptimal for any $delta = o(1)$, and give a new identity tester that achieves the optimal sample complexity. Our new upper and lower bounds show that the optimal sample complexity of identity testing is [ Thetaleft( frac{1}{epsilon^2}left(sqrt{n log(1/delta)} + log(1/delta) right)right) ] for any $n, epsilon$, and $delta$. For the special case of uniformity testing, where the given distribution is the uniform distribution $U_n$ over the domain, our new tester is surprisingly simple: to test whether $p = U_n$ versus $mathrm{d}_{TV}(p, U_n) geq epsilon$, we simply threshold $mathrm{d}_{TV}(hat{p}, U_n)$, where $hat{p}$ is the empirical probability distribution. We believe that our novel analysis techniques may be useful for other distribution testing problems as well." @default.
- W2887289949 created "2018-08-22" @default.
- W2887289949 creator A5054966819 @default.
- W2887289949 creator A5058035877 @default.
- W2887289949 creator A5058487388 @default.
- W2887289949 creator A5083990461 @default.
- W2887289949 date "2017-01-01" @default.
- W2887289949 modified "2023-09-28" @default.
- W2887289949 title "Sample-Optimal Identity Testing with High Probability." @default.
- W2887289949 hasPublicationYear "2017" @default.
- W2887289949 type Work @default.
- W2887289949 sameAs 2887289949 @default.
- W2887289949 citedByCount "2" @default.
- W2887289949 countsByYear W28872899492018 @default.
- W2887289949 countsByYear W28872899492019 @default.
- W2887289949 crossrefType "journal-article" @default.
- W2887289949 hasAuthorship W2887289949A5054966819 @default.
- W2887289949 hasAuthorship W2887289949A5058035877 @default.
- W2887289949 hasAuthorship W2887289949A5058487388 @default.
- W2887289949 hasAuthorship W2887289949A5083990461 @default.
- W2887289949 hasConcept C105795698 @default.
- W2887289949 hasConcept C110121322 @default.
- W2887289949 hasConcept C114614502 @default.
- W2887289949 hasConcept C118615104 @default.
- W2887289949 hasConcept C121332964 @default.
- W2887289949 hasConcept C134306372 @default.
- W2887289949 hasConcept C149441793 @default.
- W2887289949 hasConcept C24890656 @default.
- W2887289949 hasConcept C2778355321 @default.
- W2887289949 hasConcept C2779557605 @default.
- W2887289949 hasConcept C33923547 @default.
- W2887289949 hasConcept C62520636 @default.
- W2887289949 hasConcept C77553402 @default.
- W2887289949 hasConceptScore W2887289949C105795698 @default.
- W2887289949 hasConceptScore W2887289949C110121322 @default.
- W2887289949 hasConceptScore W2887289949C114614502 @default.
- W2887289949 hasConceptScore W2887289949C118615104 @default.
- W2887289949 hasConceptScore W2887289949C121332964 @default.
- W2887289949 hasConceptScore W2887289949C134306372 @default.
- W2887289949 hasConceptScore W2887289949C149441793 @default.
- W2887289949 hasConceptScore W2887289949C24890656 @default.
- W2887289949 hasConceptScore W2887289949C2778355321 @default.
- W2887289949 hasConceptScore W2887289949C2779557605 @default.
- W2887289949 hasConceptScore W2887289949C33923547 @default.
- W2887289949 hasConceptScore W2887289949C62520636 @default.
- W2887289949 hasConceptScore W2887289949C77553402 @default.
- W2887289949 hasLocation W28872899491 @default.
- W2887289949 hasOpenAccess W2887289949 @default.
- W2887289949 hasPrimaryLocation W28872899491 @default.
- W2887289949 hasRelatedWork W145288388 @default.
- W2887289949 hasRelatedWork W1832337710 @default.
- W2887289949 hasRelatedWork W1997236071 @default.
- W2887289949 hasRelatedWork W2015703626 @default.
- W2887289949 hasRelatedWork W2042587503 @default.
- W2887289949 hasRelatedWork W2072451764 @default.
- W2887289949 hasRelatedWork W2103839576 @default.
- W2887289949 hasRelatedWork W2265417789 @default.
- W2887289949 hasRelatedWork W2320813313 @default.
- W2887289949 hasRelatedWork W2510082553 @default.
- W2887289949 hasRelatedWork W2789163852 @default.
- W2887289949 hasRelatedWork W2907664639 @default.
- W2887289949 hasRelatedWork W2910196412 @default.
- W2887289949 hasRelatedWork W2942031148 @default.
- W2887289949 hasRelatedWork W2952310156 @default.
- W2887289949 hasRelatedWork W2963478756 @default.
- W2887289949 hasRelatedWork W2972249936 @default.
- W2887289949 hasRelatedWork W2986767612 @default.
- W2887289949 hasRelatedWork W3006963017 @default.
- W2887289949 hasRelatedWork W320897796 @default.
- W2887289949 hasVolume "24" @default.
- W2887289949 isParatext "false" @default.
- W2887289949 isRetracted "false" @default.
- W2887289949 magId "2887289949" @default.
- W2887289949 workType "article" @default.