Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962841567> ?p ?o ?g. }
- W2962841567 endingPage "2619" @default.
- W2962841567 startingPage "2611" @default.
- W2962841567 abstract "We consider the problem of testing whether two unequal-sized samples were drawn from identical distributions, versus distributions that differ significantly. Specifically, given a target error parameter e > 0, m1 independent draws from an unknown distribution p with discrete support, and m2 draws from an unknown distribution q of discrete support, we describe a test for distinguishing the case that p = q from the case that ‖p - q‖1 ≥ e. If p and q are supported on at most n elements, then our test is successful with high probability provided m1 ≥ n2/3/e4/3 and m2 = Ω (max{n/√m1 e2, √n/e2}). We show that this tradeoff is information theoretically optimal throughout this range in the dependencies on all parameters, n, m1, and e, to constant factors for worst-case distributions. As a consequence, we obtain an algorithm for estimating the mixing time of a Markov chain on n states up to a log n factor that uses O(n3/2τmix) queries to a next node oracle. The core of our testing algorithm is a relatively simple statistic that seems to perform well in practice, both on synthetic and on natural language data. We believe that this statistic might prove to be a useful primitive within larger machine learning and natural language processing systems." @default.
- W2962841567 created "2019-07-30" @default.
- W2962841567 creator A5052870102 @default.
- W2962841567 creator A5079503799 @default.
- W2962841567 date "2015-12-07" @default.
- W2962841567 modified "2023-09-24" @default.
- W2962841567 title "Testing closeness with unequal sized samples" @default.
- W2962841567 cites W1501167079 @default.
- W2962841567 cites W1575031463 @default.
- W2962841567 cites W1580631876 @default.
- W2962841567 cites W1600293573 @default.
- W2962841567 cites W1982516282 @default.
- W2962841567 cites W1987754412 @default.
- W2962841567 cites W1988624553 @default.
- W2962841567 cites W2000163531 @default.
- W2962841567 cites W2015579414 @default.
- W2962841567 cites W2058991275 @default.
- W2962841567 cites W2072211488 @default.
- W2962841567 cites W2076381458 @default.
- W2962841567 cites W2078764670 @default.
- W2962841567 cites W2094608047 @default.
- W2962841567 cites W2102942501 @default.
- W2962841567 cites W2104648144 @default.
- W2962841567 cites W2105433123 @default.
- W2962841567 cites W2114771311 @default.
- W2962841567 cites W2124055802 @default.
- W2962841567 cites W2127090196 @default.
- W2962841567 cites W2134169350 @default.
- W2962841567 cites W2138256420 @default.
- W2962841567 cites W2151647902 @default.
- W2962841567 cites W2159784709 @default.
- W2962841567 cites W2170990775 @default.
- W2962841567 cites W2182991033 @default.
- W2962841567 cites W2187447858 @default.
- W2962841567 cites W2401195433 @default.
- W2962841567 cites W2962933746 @default.
- W2962841567 cites W2963920131 @default.
- W2962841567 hasPublicationYear "2015" @default.
- W2962841567 type Work @default.
- W2962841567 sameAs 2962841567 @default.
- W2962841567 citedByCount "14" @default.
- W2962841567 countsByYear W29628415672015 @default.
- W2962841567 countsByYear W29628415672016 @default.
- W2962841567 countsByYear W29628415672018 @default.
- W2962841567 countsByYear W29628415672019 @default.
- W2962841567 countsByYear W29628415672020 @default.
- W2962841567 countsByYear W29628415672021 @default.
- W2962841567 crossrefType "proceedings-article" @default.
- W2962841567 hasAuthorship W2962841567A5052870102 @default.
- W2962841567 hasAuthorship W2962841567A5079503799 @default.
- W2962841567 hasConcept C105795698 @default.
- W2962841567 hasConcept C110121322 @default.
- W2962841567 hasConcept C11413529 @default.
- W2962841567 hasConcept C114614502 @default.
- W2962841567 hasConcept C115903868 @default.
- W2962841567 hasConcept C118615104 @default.
- W2962841567 hasConcept C123842658 @default.
- W2962841567 hasConcept C134306372 @default.
- W2962841567 hasConcept C149441793 @default.
- W2962841567 hasConcept C159985019 @default.
- W2962841567 hasConcept C169857963 @default.
- W2962841567 hasConcept C192562407 @default.
- W2962841567 hasConcept C199360897 @default.
- W2962841567 hasConcept C204323151 @default.
- W2962841567 hasConcept C2777027219 @default.
- W2962841567 hasConcept C2779545769 @default.
- W2962841567 hasConcept C33923547 @default.
- W2962841567 hasConcept C41008148 @default.
- W2962841567 hasConcept C55166926 @default.
- W2962841567 hasConcept C87007009 @default.
- W2962841567 hasConcept C89128539 @default.
- W2962841567 hasConcept C98763669 @default.
- W2962841567 hasConceptScore W2962841567C105795698 @default.
- W2962841567 hasConceptScore W2962841567C110121322 @default.
- W2962841567 hasConceptScore W2962841567C11413529 @default.
- W2962841567 hasConceptScore W2962841567C114614502 @default.
- W2962841567 hasConceptScore W2962841567C115903868 @default.
- W2962841567 hasConceptScore W2962841567C118615104 @default.
- W2962841567 hasConceptScore W2962841567C123842658 @default.
- W2962841567 hasConceptScore W2962841567C134306372 @default.
- W2962841567 hasConceptScore W2962841567C149441793 @default.
- W2962841567 hasConceptScore W2962841567C159985019 @default.
- W2962841567 hasConceptScore W2962841567C169857963 @default.
- W2962841567 hasConceptScore W2962841567C192562407 @default.
- W2962841567 hasConceptScore W2962841567C199360897 @default.
- W2962841567 hasConceptScore W2962841567C204323151 @default.
- W2962841567 hasConceptScore W2962841567C2777027219 @default.
- W2962841567 hasConceptScore W2962841567C2779545769 @default.
- W2962841567 hasConceptScore W2962841567C33923547 @default.
- W2962841567 hasConceptScore W2962841567C41008148 @default.
- W2962841567 hasConceptScore W2962841567C55166926 @default.
- W2962841567 hasConceptScore W2962841567C87007009 @default.
- W2962841567 hasConceptScore W2962841567C89128539 @default.
- W2962841567 hasConceptScore W2962841567C98763669 @default.
- W2962841567 hasLocation W29628415671 @default.
- W2962841567 hasOpenAccess W2962841567 @default.
- W2962841567 hasPrimaryLocation W29628415671 @default.
- W2962841567 hasRelatedWork W1501167079 @default.