Matches in SemOpenAlex for { <https://semopenalex.org/work/W1951330496> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1951330496 abstract "Learning to rank is a supervised learning problem where the output space is the space of rankings but the supervision space is the space of relevance scores. We make theoretical contributions to the learning to rank problem both in the online and batch settings. First, we propose a perceptron-like algorithm for learning a ranking function in an online setting. Our algorithm is an extension of the classic perceptron algorithm for the classification problem. Second, in the setting of batch learning, we introduce a sufficient condition for convex ranking surrogates to ensure a generalization bound that is independent of number of objects per query. Our bound holds when linear ranking functions are used: a common practice in many learning to rank algorithms. En route to developing the online algorithm and generalization bound, we propose a novel family of listwise large margin ranking surrogates. Our novel surrogate family is obtained by modifying a well-known pairwise large margin ranking surrogate and is distinct from the listwise large margin surrogates developed using the structured prediction framework. Using the proposed family, we provide a guaranteed upper bound on the cumulative NDCG (or MAP) induced loss under the perceptron-like algorithm. We also show that the novel surrogates satisfy the generalization bound condition." @default.
- W1951330496 created "2016-06-24" @default.
- W1951330496 creator A5051918150 @default.
- W1951330496 creator A5068030920 @default.
- W1951330496 date "2014-05-03" @default.
- W1951330496 modified "2023-09-27" @default.
- W1951330496 title "Perceptron-like Algorithms and Generalization Bounds for Learning to Rank" @default.
- W1951330496 cites W2047778511 @default.
- W1951330496 cites W2051928158 @default.
- W1951330496 cites W2069870183 @default.
- W1951330496 cites W2077723394 @default.
- W1951330496 cites W2107890099 @default.
- W1951330496 cites W2108862644 @default.
- W1951330496 cites W2127176025 @default.
- W1951330496 cites W2129245267 @default.
- W1951330496 cites W2142537246 @default.
- W1951330496 cites W2142697503 @default.
- W1951330496 cites W2143331230 @default.
- W1951330496 cites W2148825261 @default.
- W1951330496 cites W2171541062 @default.
- W1951330496 cites W2296319761 @default.
- W1951330496 cites W2884580467 @default.
- W1951330496 cites W2988119488 @default.
- W1951330496 hasPublicationYear "2014" @default.
- W1951330496 type Work @default.
- W1951330496 sameAs 1951330496 @default.
- W1951330496 citedByCount "2" @default.
- W1951330496 countsByYear W19513304962015 @default.
- W1951330496 crossrefType "posted-content" @default.
- W1951330496 hasAuthorship W1951330496A5051918150 @default.
- W1951330496 hasAuthorship W1951330496A5068030920 @default.
- W1951330496 hasConcept C11413529 @default.
- W1951330496 hasConcept C114614502 @default.
- W1951330496 hasConcept C119857082 @default.
- W1951330496 hasConcept C124975894 @default.
- W1951330496 hasConcept C134306372 @default.
- W1951330496 hasConcept C154945302 @default.
- W1951330496 hasConcept C164226766 @default.
- W1951330496 hasConcept C177148314 @default.
- W1951330496 hasConcept C184898388 @default.
- W1951330496 hasConcept C189430467 @default.
- W1951330496 hasConcept C33923547 @default.
- W1951330496 hasConcept C41008148 @default.
- W1951330496 hasConcept C50644808 @default.
- W1951330496 hasConcept C60908668 @default.
- W1951330496 hasConcept C774472 @default.
- W1951330496 hasConcept C77553402 @default.
- W1951330496 hasConcept C86037889 @default.
- W1951330496 hasConceptScore W1951330496C11413529 @default.
- W1951330496 hasConceptScore W1951330496C114614502 @default.
- W1951330496 hasConceptScore W1951330496C119857082 @default.
- W1951330496 hasConceptScore W1951330496C124975894 @default.
- W1951330496 hasConceptScore W1951330496C134306372 @default.
- W1951330496 hasConceptScore W1951330496C154945302 @default.
- W1951330496 hasConceptScore W1951330496C164226766 @default.
- W1951330496 hasConceptScore W1951330496C177148314 @default.
- W1951330496 hasConceptScore W1951330496C184898388 @default.
- W1951330496 hasConceptScore W1951330496C189430467 @default.
- W1951330496 hasConceptScore W1951330496C33923547 @default.
- W1951330496 hasConceptScore W1951330496C41008148 @default.
- W1951330496 hasConceptScore W1951330496C50644808 @default.
- W1951330496 hasConceptScore W1951330496C60908668 @default.
- W1951330496 hasConceptScore W1951330496C774472 @default.
- W1951330496 hasConceptScore W1951330496C77553402 @default.
- W1951330496 hasConceptScore W1951330496C86037889 @default.
- W1951330496 hasLocation W19513304961 @default.
- W1951330496 hasOpenAccess W1951330496 @default.
- W1951330496 hasPrimaryLocation W19513304961 @default.
- W1951330496 hasRelatedWork W1483952878 @default.
- W1951330496 hasRelatedWork W1535249499 @default.
- W1951330496 hasRelatedWork W1572401054 @default.
- W1951330496 hasRelatedWork W1578240932 @default.
- W1951330496 hasRelatedWork W1604002124 @default.
- W1951330496 hasRelatedWork W182640454 @default.
- W1951330496 hasRelatedWork W2122350398 @default.
- W1951330496 hasRelatedWork W2144064004 @default.
- W1951330496 hasRelatedWork W2149433471 @default.
- W1951330496 hasRelatedWork W2171743041 @default.
- W1951330496 hasRelatedWork W2188523697 @default.
- W1951330496 hasRelatedWork W2221175859 @default.
- W1951330496 hasRelatedWork W2945670763 @default.
- W1951330496 hasRelatedWork W2971325325 @default.
- W1951330496 hasRelatedWork W2991274409 @default.
- W1951330496 hasRelatedWork W3024540227 @default.
- W1951330496 hasRelatedWork W3091360173 @default.
- W1951330496 hasRelatedWork W3170504989 @default.
- W1951330496 hasRelatedWork W626007939 @default.
- W1951330496 hasRelatedWork W2572787705 @default.
- W1951330496 isParatext "false" @default.
- W1951330496 isRetracted "false" @default.
- W1951330496 magId "1951330496" @default.
- W1951330496 workType "article" @default.