FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2419099043> ?p ?o ?g. }

• W2419099043 abstract "We consider the following basic learning task: given independent draws from an unknown distribution over a discrete support, output an approximation of the distribution that is as accurate as possible in L1 distance (equivalently, total variation distance, or statistical distance). Perhaps surprisingly, it is often possible to de-noise the empirical distribution of the samples to return an approximation of the true distribution that is significantly more accurate than the empirical distribution, without relying on any prior assumptions on the distribution. We present an instance optimal learning algorithm which optimally performs this de-noising for every distribution for which such a de-noising is possible. More formally, given n independent draws from a distribution p, our algorithm returns a labelled vector whose expected distance from p is equal to the minimum possible expected error that could be obtained by any algorithm, even one that is given the true unlabeled vector of probabilities of distribution p and simply needs to assign labels---up to an additive subconstant term that is independent of p and goes to zero as n gets large. This somewhat surprising result has several conceptual implications, including the fact that, for any large sample from a distribution over discrete support, prior knowledge of the rates of decay of the tails of the distribution (e.g. power-law type assumptions) is not significantly helpful for the task of learning the distribution. As a consequence of our techniques, we also show that given a set of n samples from an arbitrary distribution, one can accurately estimate the expected number of distinct elements that will be observed in a sample of any size up to n log n. This sort of extrapolation is practically relevant, particularly to domains such as genomics where it is important to understand how much more might be discovered given larger sample sizes, and we are optimistic that our approach is practically viable." @default.
• W2419099043 created "2016-06-24" @default.
• W2419099043 creator A5036230157 @default.
• W2419099043 creator A5079503799 @default.
• W2419099043 date "2016-06-19" @default.
• W2419099043 modified "2023-09-24" @default.
• W2419099043 title "Instance optimal learning of discrete distributions" @default.
• W2419099043 cites W1982918157 @default.
• W2419099043 cites W1989151402 @default.
• W2419099043 cites W2000163531 @default.
• W2419099043 cites W2002001845 @default.
• W2419099043 cites W2063918473 @default.
• W2419099043 cites W2069241007 @default.
• W2419099043 cites W2078764670 @default.
• W2419099043 cites W2082092506 @default.
• W2419099043 cites W2095306947 @default.
• W2419099043 cites W2104549677 @default.
• W2419099043 cites W2105433123 @default.
• W2419099043 cites W2127090196 @default.
• W2419099043 cites W2129311580 @default.
• W2419099043 cites W2143122862 @default.
• W2419099043 cites W2143602768 @default.
• W2419099043 cites W2158195707 @default.
• W2419099043 cites W2291181759 @default.
• W2419099043 cites W2305509242 @default.
• W2419099043 cites W2963424608 @default.
• W2419099043 doi "https://doi.org/10.1145/2897518.2897641" @default.
• W2419099043 hasPublicationYear "2016" @default.
• W2419099043 type Work @default.
• W2419099043 sameAs 2419099043 @default.
• W2419099043 citedByCount "40" @default.
• W2419099043 countsByYear W24190990432016 @default.
• W2419099043 countsByYear W24190990432017 @default.
• W2419099043 countsByYear W24190990432018 @default.
• W2419099043 countsByYear W24190990432019 @default.
• W2419099043 countsByYear W24190990432020 @default.
• W2419099043 countsByYear W24190990432021 @default.
• W2419099043 countsByYear W24190990432023 @default.
• W2419099043 crossrefType "proceedings-article" @default.
• W2419099043 hasAuthorship W2419099043A5036230157 @default.
• W2419099043 hasAuthorship W2419099043A5079503799 @default.
• W2419099043 hasBestOaLocation W24190990431 @default.
• W2419099043 hasConcept C105795698 @default.
• W2419099043 hasConcept C110121322 @default.
• W2419099043 hasConcept C11413529 @default.
• W2419099043 hasConcept C126255220 @default.
• W2419099043 hasConcept C134306372 @default.
• W2419099043 hasConcept C149441793 @default.
• W2419099043 hasConcept C1602530 @default.
• W2419099043 hasConcept C160947583 @default.
• W2419099043 hasConcept C167723999 @default.
• W2419099043 hasConcept C33923547 @default.
• W2419099043 hasConcept C57205106 @default.
• W2419099043 hasConcept C58948655 @default.
• W2419099043 hasConcept C67926830 @default.
• W2419099043 hasConcept C98385598 @default.
• W2419099043 hasConceptScore W2419099043C105795698 @default.
• W2419099043 hasConceptScore W2419099043C110121322 @default.
• W2419099043 hasConceptScore W2419099043C11413529 @default.
• W2419099043 hasConceptScore W2419099043C126255220 @default.
• W2419099043 hasConceptScore W2419099043C134306372 @default.
• W2419099043 hasConceptScore W2419099043C149441793 @default.
• W2419099043 hasConceptScore W2419099043C1602530 @default.
• W2419099043 hasConceptScore W2419099043C160947583 @default.
• W2419099043 hasConceptScore W2419099043C167723999 @default.
• W2419099043 hasConceptScore W2419099043C33923547 @default.
• W2419099043 hasConceptScore W2419099043C57205106 @default.
• W2419099043 hasConceptScore W2419099043C58948655 @default.
• W2419099043 hasConceptScore W2419099043C67926830 @default.
• W2419099043 hasConceptScore W2419099043C98385598 @default.
• W2419099043 hasFunder F4320306076 @default.
• W2419099043 hasFunder F4320306151 @default.
• W2419099043 hasLocation W24190990431 @default.
• W2419099043 hasOpenAccess W2419099043 @default.
• W2419099043 hasPrimaryLocation W24190990431 @default.
• W2419099043 hasRelatedWork W1562004654 @default.
• W2419099043 hasRelatedWork W1698563072 @default.
• W2419099043 hasRelatedWork W2046099583 @default.
• W2419099043 hasRelatedWork W2159804555 @default.
• W2419099043 hasRelatedWork W2363131693 @default.
• W2419099043 hasRelatedWork W2419099043 @default.
• W2419099043 hasRelatedWork W2518230766 @default.
• W2419099043 hasRelatedWork W2808578155 @default.
• W2419099043 hasRelatedWork W3187496908 @default.
• W2419099043 hasRelatedWork W3192728548 @default.
• W2419099043 isParatext "false" @default.
• W2419099043 isRetracted "false" @default.
• W2419099043 magId "2419099043" @default.
• W2419099043 workType "article" @default.