Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885016504> ?p ?o ?g. }
- W2885016504 abstract "We study the problem of supervised learning a metric space under discriminative constraints. Given a universe $X$ and sets ${cal S}, {cal D}subset {X choose 2}$ of similar and dissimilar pairs, we seek to find a mapping $f:Xto Y$, into some target metric space $M=(Y,rho)$, such that similar objects are mapped to points at distance at most $u$, and dissimilar objects are mapped to points at distance at least $ell$. More generally, the goal is to find a mapping of maximum accuracy (that is, fraction of correctly classified pairs). We propose approximation algorithms for various versions of this problem, for the cases of Euclidean and tree metric spaces. For both of these target spaces, we obtain fully polynomial-time approximation schemes (FPTAS) for the case of perfect information. In the presence of imperfect information we present approximation algorithms that run in quasipolynomial time (QPTAS). Our algorithms use a combination of tools from metric embeddings and graph partitioning, that could be of independent interest." @default.
- W2885016504 created "2018-08-03" @default.
- W2885016504 creator A5008301868 @default.
- W2885016504 creator A5013188587 @default.
- W2885016504 creator A5089268692 @default.
- W2885016504 date "2018-07-13" @default.
- W2885016504 modified "2023-09-27" @default.
- W2885016504 title "Algorithms for metric learning via contrastive embeddings." @default.
- W2885016504 cites W1499673022 @default.
- W2885016504 cites W1586283311 @default.
- W2885016504 cites W1952648253 @default.
- W2885016504 cites W1982378203 @default.
- W2885016504 cites W2009861473 @default.
- W2885016504 cites W2011935680 @default.
- W2885016504 cites W2012238497 @default.
- W2885016504 cites W2028203362 @default.
- W2885016504 cites W2042899161 @default.
- W2885016504 cites W2072858942 @default.
- W2885016504 cites W2088658556 @default.
- W2885016504 cites W2088844265 @default.
- W2885016504 cites W2106053110 @default.
- W2885016504 cites W2114493937 @default.
- W2885016504 cites W2121949863 @default.
- W2885016504 cites W2124577064 @default.
- W2885016504 cites W2144367957 @default.
- W2885016504 cites W2149726280 @default.
- W2885016504 cites W2154876245 @default.
- W2885016504 cites W2156397150 @default.
- W2885016504 cites W2157364932 @default.
- W2885016504 cites W2169495281 @default.
- W2885016504 cites W2176446742 @default.
- W2885016504 cites W2397920857 @default.
- W2885016504 cites W2569466538 @default.
- W2885016504 cites W2914959486 @default.
- W2885016504 cites W2199123782 @default.
- W2885016504 hasPublicationYear "2018" @default.
- W2885016504 type Work @default.
- W2885016504 sameAs 2885016504 @default.
- W2885016504 citedByCount "0" @default.
- W2885016504 crossrefType "posted-content" @default.
- W2885016504 hasAuthorship W2885016504A5008301868 @default.
- W2885016504 hasAuthorship W2885016504A5013188587 @default.
- W2885016504 hasAuthorship W2885016504A5089268692 @default.
- W2885016504 hasConcept C111919701 @default.
- W2885016504 hasConcept C11413529 @default.
- W2885016504 hasConcept C114614502 @default.
- W2885016504 hasConcept C118615104 @default.
- W2885016504 hasConcept C129782007 @default.
- W2885016504 hasConcept C132525143 @default.
- W2885016504 hasConcept C148764684 @default.
- W2885016504 hasConcept C154945302 @default.
- W2885016504 hasConcept C162324750 @default.
- W2885016504 hasConcept C176217482 @default.
- W2885016504 hasConcept C182964748 @default.
- W2885016504 hasConcept C186450821 @default.
- W2885016504 hasConcept C198043062 @default.
- W2885016504 hasConcept C21547014 @default.
- W2885016504 hasConcept C2524010 @default.
- W2885016504 hasConcept C2778572836 @default.
- W2885016504 hasConcept C33923547 @default.
- W2885016504 hasConcept C41008148 @default.
- W2885016504 hasConcept C97931131 @default.
- W2885016504 hasConceptScore W2885016504C111919701 @default.
- W2885016504 hasConceptScore W2885016504C11413529 @default.
- W2885016504 hasConceptScore W2885016504C114614502 @default.
- W2885016504 hasConceptScore W2885016504C118615104 @default.
- W2885016504 hasConceptScore W2885016504C129782007 @default.
- W2885016504 hasConceptScore W2885016504C132525143 @default.
- W2885016504 hasConceptScore W2885016504C148764684 @default.
- W2885016504 hasConceptScore W2885016504C154945302 @default.
- W2885016504 hasConceptScore W2885016504C162324750 @default.
- W2885016504 hasConceptScore W2885016504C176217482 @default.
- W2885016504 hasConceptScore W2885016504C182964748 @default.
- W2885016504 hasConceptScore W2885016504C186450821 @default.
- W2885016504 hasConceptScore W2885016504C198043062 @default.
- W2885016504 hasConceptScore W2885016504C21547014 @default.
- W2885016504 hasConceptScore W2885016504C2524010 @default.
- W2885016504 hasConceptScore W2885016504C2778572836 @default.
- W2885016504 hasConceptScore W2885016504C33923547 @default.
- W2885016504 hasConceptScore W2885016504C41008148 @default.
- W2885016504 hasConceptScore W2885016504C97931131 @default.
- W2885016504 hasLocation W28850165041 @default.
- W2885016504 hasOpenAccess W2885016504 @default.
- W2885016504 hasPrimaryLocation W28850165041 @default.
- W2885016504 hasRelatedWork W1511554697 @default.
- W2885016504 hasRelatedWork W1982829297 @default.
- W2885016504 hasRelatedWork W1993265270 @default.
- W2885016504 hasRelatedWork W2001514895 @default.
- W2885016504 hasRelatedWork W2031013430 @default.
- W2885016504 hasRelatedWork W2086041184 @default.
- W2885016504 hasRelatedWork W2124177747 @default.
- W2885016504 hasRelatedWork W2296861909 @default.
- W2885016504 hasRelatedWork W2555479603 @default.
- W2885016504 hasRelatedWork W2782076782 @default.
- W2885016504 hasRelatedWork W2785833512 @default.
- W2885016504 hasRelatedWork W2902132144 @default.
- W2885016504 hasRelatedWork W2949677953 @default.
- W2885016504 hasRelatedWork W2952834167 @default.
- W2885016504 hasRelatedWork W2963330512 @default.
- W2885016504 hasRelatedWork W2964259376 @default.