Matches in SemOpenAlex for { <https://semopenalex.org/work/W1964108907> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1964108907 endingPage "47" @default.
- W1964108907 startingPage "22" @default.
- W1964108907 abstract "We investigate the computational complexity of the task of detecting dense regions of an unknown distribution from unlabeled samples of this distribution. We introduce a formal learning model for this task that uses a hypothesis class as it “anti-overfitting” mechanism. The learning task in our model can be reduced to a combinatorial optimization problem. We can show that for some constants, depending on the hypothesis class, these problems are N P -hard to approximate to within these constant factors. We go on and introduce a new criterion for the success of approximate optimization geometric problems. The new criterion requires that the algorithm competes with hypotheses only on the points that are separated by some margin μ from their boundaries. Quite surprisingly, we discover that for each of the two hypothesis classes that we investigate, there is a “critical value” of the margin parameter μ . For any value below the critical value the problems are N P -hard to approximate, while, once this value is exceeded, the problems become poly-time solvable." @default.
- W1964108907 created "2016-06-24" @default.
- W1964108907 creator A5010258967 @default.
- W1964108907 creator A5011288864 @default.
- W1964108907 creator A5032272542 @default.
- W1964108907 date "2002-02-01" @default.
- W1964108907 modified "2023-09-28" @default.
- W1964108907 title "The Computational Complexity of Densest Region Detection" @default.
- W1964108907 cites W1969530712 @default.
- W1964108907 cites W2005530305 @default.
- W1964108907 cites W2053113791 @default.
- W1964108907 cites W2087226760 @default.
- W1964108907 cites W2129889866 @default.
- W1964108907 cites W4248693963 @default.
- W1964108907 doi "https://doi.org/10.1006/jcss.2001.1797" @default.
- W1964108907 hasPublicationYear "2002" @default.
- W1964108907 type Work @default.
- W1964108907 sameAs 1964108907 @default.
- W1964108907 citedByCount "16" @default.
- W1964108907 countsByYear W19641089072012 @default.
- W1964108907 countsByYear W19641089072013 @default.
- W1964108907 countsByYear W19641089072016 @default.
- W1964108907 countsByYear W19641089072017 @default.
- W1964108907 countsByYear W19641089072018 @default.
- W1964108907 countsByYear W19641089072019 @default.
- W1964108907 countsByYear W19641089072020 @default.
- W1964108907 countsByYear W19641089072023 @default.
- W1964108907 crossrefType "journal-article" @default.
- W1964108907 hasAuthorship W1964108907A5010258967 @default.
- W1964108907 hasAuthorship W1964108907A5011288864 @default.
- W1964108907 hasAuthorship W1964108907A5032272542 @default.
- W1964108907 hasBestOaLocation W19641089071 @default.
- W1964108907 hasConcept C110121322 @default.
- W1964108907 hasConcept C11413529 @default.
- W1964108907 hasConcept C119857082 @default.
- W1964108907 hasConcept C126255220 @default.
- W1964108907 hasConcept C134306372 @default.
- W1964108907 hasConcept C154945302 @default.
- W1964108907 hasConcept C162324750 @default.
- W1964108907 hasConcept C179799912 @default.
- W1964108907 hasConcept C187736073 @default.
- W1964108907 hasConcept C199360897 @default.
- W1964108907 hasConcept C22019652 @default.
- W1964108907 hasConcept C2776291640 @default.
- W1964108907 hasConcept C2777027219 @default.
- W1964108907 hasConcept C2777212361 @default.
- W1964108907 hasConcept C2780451532 @default.
- W1964108907 hasConcept C33923547 @default.
- W1964108907 hasConcept C41008148 @default.
- W1964108907 hasConcept C50644808 @default.
- W1964108907 hasConcept C774472 @default.
- W1964108907 hasConceptScore W1964108907C110121322 @default.
- W1964108907 hasConceptScore W1964108907C11413529 @default.
- W1964108907 hasConceptScore W1964108907C119857082 @default.
- W1964108907 hasConceptScore W1964108907C126255220 @default.
- W1964108907 hasConceptScore W1964108907C134306372 @default.
- W1964108907 hasConceptScore W1964108907C154945302 @default.
- W1964108907 hasConceptScore W1964108907C162324750 @default.
- W1964108907 hasConceptScore W1964108907C179799912 @default.
- W1964108907 hasConceptScore W1964108907C187736073 @default.
- W1964108907 hasConceptScore W1964108907C199360897 @default.
- W1964108907 hasConceptScore W1964108907C22019652 @default.
- W1964108907 hasConceptScore W1964108907C2776291640 @default.
- W1964108907 hasConceptScore W1964108907C2777027219 @default.
- W1964108907 hasConceptScore W1964108907C2777212361 @default.
- W1964108907 hasConceptScore W1964108907C2780451532 @default.
- W1964108907 hasConceptScore W1964108907C33923547 @default.
- W1964108907 hasConceptScore W1964108907C41008148 @default.
- W1964108907 hasConceptScore W1964108907C50644808 @default.
- W1964108907 hasConceptScore W1964108907C774472 @default.
- W1964108907 hasIssue "1" @default.
- W1964108907 hasLocation W19641089071 @default.
- W1964108907 hasLocation W19641089072 @default.
- W1964108907 hasOpenAccess W1964108907 @default.
- W1964108907 hasPrimaryLocation W19641089071 @default.
- W1964108907 hasRelatedWork W1828744063 @default.
- W1964108907 hasRelatedWork W1964108907 @default.
- W1964108907 hasRelatedWork W2364253268 @default.
- W1964108907 hasRelatedWork W2791824431 @default.
- W1964108907 hasRelatedWork W2989932438 @default.
- W1964108907 hasRelatedWork W3099765033 @default.
- W1964108907 hasRelatedWork W3159087789 @default.
- W1964108907 hasRelatedWork W4285802257 @default.
- W1964108907 hasRelatedWork W4304731163 @default.
- W1964108907 hasRelatedWork W65304277 @default.
- W1964108907 hasVolume "64" @default.
- W1964108907 isParatext "false" @default.
- W1964108907 isRetracted "false" @default.
- W1964108907 magId "1964108907" @default.
- W1964108907 workType "article" @default.