FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1617587412> ?p ?o ?g. }

• W1617587412 abstract "Structured sparsity is an important modeling tool that expands the applicability of convex formulations for data analysis, however it also creates significant challenges for efficient algorithm design. In this paper we investigate the generalized conditional gradient (GCG) algorithm for solving structured sparse optimization problems---demonstrating that, with some enhancements, it can provide a more efficient alternative to current state of the art approaches. After providing a comprehensive overview of the convergence properties of GCG, we develop efficient methods for evaluating polar operators, a subroutine that is required in each GCG iteration. In particular, we show how the polar operator can be efficiently evaluated in two important scenarios: dictionary learning and structured sparse estimation. A further improvement is achieved by interleaving GCG with fixed-rank local subspace optimization. A series of experiments on matrix completion, multi-class classification, multi-view dictionary learning and overlapping group lasso shows that the proposed method can significantly reduce the training cost of current alternatives." @default.
• W1617587412 created "2016-06-24" @default.
• W1617587412 creator A5010575626 @default.
• W1617587412 creator A5038911681 @default.
• W1617587412 creator A5083780440 @default.
• W1617587412 date "2014-10-17" @default.
• W1617587412 modified "2023-09-23" @default.
• W1617587412 title "Generalized Conditional Gradient for Sparse Estimation" @default.
• W1617587412 cites W1490256991 @default.
• W1617587412 cites W1497745584 @default.
• W1617587412 cites W1516903196 @default.
• W1617587412 cites W1539012881 @default.
• W1617587412 cites W1551360398 @default.
• W1617587412 cites W1574851760 @default.
• W1617587412 cites W1775587472 @default.
• W1617587412 cites W1902027874 @default.
• W1617587412 cites W1963547452 @default.
• W1617587412 cites W1966096622 @default.
• W1617587412 cites W1967956032 @default.
• W1617587412 cites W1970554427 @default.
• W1617587412 cites W1971791211 @default.
• W1617587412 cites W1994520254 @default.
• W1617587412 cites W1994569450 @default.
• W1617587412 cites W1998367754 @default.
• W1617587412 cites W2016384870 @default.
• W1617587412 cites W2030161963 @default.
• W1617587412 cites W2040676043 @default.
• W1617587412 cites W2057737028 @default.
• W1617587412 cites W205960364 @default.
• W1617587412 cites W2065180801 @default.
• W1617587412 cites W2074693857 @default.
• W1617587412 cites W2078735805 @default.
• W1617587412 cites W2086309650 @default.
• W1617587412 cites W2100235303 @default.
• W1617587412 cites W2100556411 @default.
• W1617587412 cites W2106890447 @default.
• W1617587412 cites W2109706083 @default.
• W1617587412 cites W2112284959 @default.
• W1617587412 cites W2114605231 @default.
• W1617587412 cites W2119821739 @default.
• W1617587412 cites W2120470041 @default.
• W1617587412 cites W2121133091 @default.
• W1617587412 cites W2121562066 @default.
• W1617587412 cites W2121966774 @default.
• W1617587412 cites W2122090912 @default.
• W1617587412 cites W2124172487 @default.
• W1617587412 cites W2125290066 @default.
• W1617587412 cites W2126418337 @default.
• W1617587412 cites W2128610923 @default.
• W1617587412 cites W2131437840 @default.
• W1617587412 cites W2135046866 @default.
• W1617587412 cites W2136885855 @default.
• W1617587412 cites W2138265962 @default.
• W1617587412 cites W2141696759 @default.
• W1617587412 cites W2145889472 @default.
• W1617587412 cites W2146682077 @default.
• W1617587412 cites W2155827809 @default.
• W1617587412 cites W2156872152 @default.
• W1617587412 cites W2168893847 @default.
• W1617587412 cites W2170402521 @default.
• W1617587412 cites W2226582656 @default.
• W1617587412 cites W2247185167 @default.
• W1617587412 cites W2339666411 @default.
• W1617587412 cites W2952139899 @default.
• W1617587412 cites W2963703858 @default.
• W1617587412 cites W905619 @default.
• W1617587412 cites W3142913680 @default.
• W1617587412 doi "https://doi.org/10.48550/arxiv.1410.4828" @default.
• W1617587412 hasPublicationYear "2014" @default.
• W1617587412 type Work @default.
• W1617587412 sameAs 1617587412 @default.
• W1617587412 citedByCount "7" @default.
• W1617587412 countsByYear W16175874122015 @default.
• W1617587412 countsByYear W16175874122016 @default.
• W1617587412 countsByYear W16175874122017 @default.
• W1617587412 countsByYear W16175874122018 @default.
• W1617587412 countsByYear W16175874122019 @default.
• W1617587412 crossrefType "posted-content" @default.
• W1617587412 hasAuthorship W1617587412A5010575626 @default.
• W1617587412 hasAuthorship W1617587412A5038911681 @default.
• W1617587412 hasAuthorship W1617587412A5083780440 @default.
• W1617587412 hasBestOaLocation W16175874121 @default.
• W1617587412 hasConcept C104317684 @default.
• W1617587412 hasConcept C10494615 @default.
• W1617587412 hasConcept C111919701 @default.
• W1617587412 hasConcept C11413529 @default.
• W1617587412 hasConcept C114614502 @default.
• W1617587412 hasConcept C119857082 @default.
• W1617587412 hasConcept C126255220 @default.
• W1617587412 hasConcept C153258448 @default.
• W1617587412 hasConcept C154945302 @default.
• W1617587412 hasConcept C158448853 @default.
• W1617587412 hasConcept C164226766 @default.
• W1617587412 hasConcept C17020691 @default.
• W1617587412 hasConcept C185592680 @default.
• W1617587412 hasConcept C28034677 @default.
• W1617587412 hasConcept C32834561 @default.
• W1617587412 hasConcept C33923547 @default.
• W1617587412 hasConcept C41008148 @default.
• W1617587412 hasConcept C50644808 @default.

• next