FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W76980307> ?p ?o ?g. }

• W76980307 abstract "The notion of Hilbert space embedding of probability measures has recently been used in various statistical applications like dimensionality reduction, homogeneity testing, independence testing, etc. This embedding represents any probability measure as a mean element in a reproducing kernel Hilbert space (RKHS). A pseudometric on the space of probability measures can be defined as the distance between distribution embeddings: we denote this as γ k, indexed by the positive definite (pd) kernel function k that defines the inner product in the RKHS. In this dissertation, various theoretical properties of γ k and the associated RKHS embedding are presented. First, in order for γ k to be useful in practice, it is essential that it is a metric and not just a pseudometric. Therefore, various easily checkable characterizations have been obtained for k so that γk is a metric (such k are referred to as characteristic kernels), in contrast to the previously published characterizations which are either difficult to check or may apply only in restricted circumstances (e.g., on compact domains). Second, the relation of characteristic kernels to the richness of RKHS--how well an RKHS approximates some target function space--and other common notions of pd kernels like strictly pd (spd), integrally spd, conditionally spd, etc., is studied. Third, the question of the nature of topology induced by γ k is studied wherein it is shown that γk associated with integrally spd kernels--a stronger notion than a characteristic kernel--metrize the weak* (weak-star) topology on the space of probability measures. Fourth, γk is compared to integral probability metrics (IPMs) and p-divergences, wherein it is shown that the empirical estimator of γ k is simple to compute and exhibits fast rate of convergence compared to those of IPMs and p-divergences. These properties make γ k to be more applicable in practice than these other families of distances. Finally, a novel notion of embedding probability measures into a reproducing kernel Banach space (RKBS) is proposed and its properties are studied. It is shown that the proposed embedding and its properties generalize their RKHS counterparts, thereby resulting in richer distance measures on the space of probabilities." @default.
• W76980307 created "2016-06-24" @default.
• W76980307 creator A5003709708 @default.
• W76980307 creator A5082408294 @default.
• W76980307 date "2010-01-01" @default.
• W76980307 modified "2023-09-23" @default.
• W76980307 title "Reproducing kernel space embeddings and metrics on probability measures" @default.
• W76980307 cites W120306724 @default.
• W76980307 cites W1480714498 @default.
• W76980307 cites W1486164486 @default.
• W76980307 cites W1500590279 @default.
• W76980307 cites W1510073064 @default.
• W76980307 cites W1515072779 @default.
• W76980307 cites W152055444 @default.
• W76980307 cites W1521379649 @default.
• W76980307 cites W1535793628 @default.
• W76980307 cites W1540155273 @default.
• W76980307 cites W1542886316 @default.
• W76980307 cites W1544839292 @default.
• W76980307 cites W1550988992 @default.
• W76980307 cites W1552416095 @default.
• W76980307 cites W1559159361 @default.
• W76980307 cites W1564947197 @default.
• W76980307 cites W1565176583 @default.
• W76980307 cites W1582706191 @default.
• W76980307 cites W1605715241 @default.
• W76980307 cites W1647376582 @default.
• W76980307 cites W1746819321 @default.
• W76980307 cites W179694669 @default.
• W76980307 cites W1946137962 @default.
• W76980307 cites W1986280275 @default.
• W76980307 cites W1988771740 @default.
• W76980307 cites W1989408439 @default.
• W76980307 cites W1994166982 @default.
• W76980307 cites W1995023786 @default.
• W76980307 cites W2002355073 @default.
• W76980307 cites W2008056655 @default.
• W76980307 cites W2010353172 @default.
• W76980307 cites W2011077222 @default.
• W76980307 cites W2016950110 @default.
• W76980307 cites W2031075370 @default.
• W76980307 cites W2032916024 @default.
• W76980307 cites W2052103094 @default.
• W76980307 cites W2053241748 @default.
• W76980307 cites W2067002097 @default.
• W76980307 cites W2072227363 @default.
• W76980307 cites W2086234878 @default.
• W76980307 cites W2086924628 @default.
• W76980307 cites W2087347434 @default.
• W76980307 cites W2089075540 @default.
• W76980307 cites W2099693464 @default.
• W76980307 cites W2100600008 @default.
• W76980307 cites W2105767494 @default.
• W76980307 cites W2111181349 @default.
• W76980307 cites W2112207221 @default.
• W76980307 cites W2112552549 @default.
• W76980307 cites W2119451546 @default.
• W76980307 cites W2119821739 @default.
• W76980307 cites W2124331852 @default.
• W76980307 cites W2125085449 @default.
• W76980307 cites W2125865219 @default.
• W76980307 cites W2128345262 @default.
• W76980307 cites W2131804466 @default.
• W76980307 cites W2131940723 @default.
• W76980307 cites W2145295623 @default.
• W76980307 cites W2148603752 @default.
• W76980307 cites W2149268774 @default.
• W76980307 cites W2149306165 @default.
• W76980307 cites W2155010204 @default.
• W76980307 cites W2157801062 @default.
• W76980307 cites W2162798864 @default.
• W76980307 cites W2166944917 @default.
• W76980307 cites W2254463431 @default.
• W76980307 cites W2296319761 @default.
• W76980307 cites W2328111639 @default.
• W76980307 cites W2475618019 @default.
• W76980307 cites W2527802255 @default.
• W76980307 cites W2579923771 @default.
• W76980307 cites W2746534045 @default.
• W76980307 cites W2797333853 @default.
• W76980307 cites W2799119698 @default.
• W76980307 cites W2913243980 @default.
• W76980307 cites W2963973173 @default.
• W76980307 cites W2989661724 @default.
• W76980307 cites W3023646433 @default.
• W76980307 cites W3038830718 @default.
• W76980307 cites W3119651796 @default.
• W76980307 cites W3127518054 @default.
• W76980307 cites W3150304496 @default.
• W76980307 cites W583278954 @default.
• W76980307 cites W583356579 @default.
• W76980307 cites W597932189 @default.
• W76980307 cites W599484449 @default.
• W76980307 cites W90602582 @default.
• W76980307 cites W91227773 @default.
• W76980307 hasPublicationYear "2010" @default.
• W76980307 type Work @default.
• W76980307 sameAs 76980307 @default.
• W76980307 citedByCount "2" @default.
• W76980307 countsByYear W769803072012 @default.

• next