FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2796758701> ?p ?o ?g. }

• W2796758701 abstract "The thresholded feature has recently emerged as an extremely efficient, yet rough empirical approximation, of the time-consuming sparse coding inference process. Such an approximation has not yet been rigorously examined, and standard dictionaries often lead to non-optimal performance when used for computing thresholded features. In this paper, we first present two theoretical recovery guarantees for the thresholded feature to exactly recover the nonzero support of the sparse code. Motivated by them, we then formulate the Dictionary Learning for Thresholded Features (DLTF) model, which learns an optimized dictionary for applying the thresholded feature. In particular, for the $(k, 2)$ norm involved, a novel proximal operator with log-linear time complexity $O(mlog m)$ is derived. We evaluate the performance of DLTF on a vast range of synthetic and real-data tasks, where DLTF demonstrates remarkable efficiency, effectiveness and robustness in all experiments. In addition, we briefly discuss the potential link between DLTF and deep learning building blocks." @default.
• W2796758701 created "2018-04-24" @default.
• W2796758701 creator A5033755969 @default.
• W2796758701 creator A5048522863 @default.
• W2796758701 creator A5049225160 @default.
• W2796758701 creator A5069376593 @default.
• W2796758701 creator A5086939495 @default.
• W2796758701 date "2018-04-16" @default.
• W2796758701 modified "2023-10-16" @default.
• W2796758701 title "Learning Simple Thresholded Features with Sparse Support Recovery" @default.
• W2796758701 cites W1686810756 @default.
• W2796758701 cites W1853900790 @default.
• W2796758701 cites W1930116263 @default.
• W2796758701 cites W1963951738 @default.
• W2796758701 cites W1980454827 @default.
• W2796758701 cites W2012833704 @default.
• W2796758701 cites W2023630749 @default.
• W2796758701 cites W2034972122 @default.
• W2796758701 cites W2042554576 @default.
• W2796758701 cites W2046351805 @default.
• W2796758701 cites W2046779692 @default.
• W2796758701 cites W2062888624 @default.
• W2796758701 cites W2086413318 @default.
• W2796758701 cites W2086953401 @default.
• W2796758701 cites W2089597365 @default.
• W2796758701 cites W2091893102 @default.
• W2796758701 cites W2099321050 @default.
• W2796758701 cites W2102129292 @default.
• W2796758701 cites W2104266187 @default.
• W2796758701 cites W2105390090 @default.
• W2796758701 cites W2112770106 @default.
• W2796758701 cites W2112796928 @default.
• W2796758701 cites W2114503967 @default.
• W2796758701 cites W2115061756 @default.
• W2796758701 cites W2115549875 @default.
• W2796758701 cites W2118858186 @default.
• W2796758701 cites W2128026227 @default.
• W2796758701 cites W2129131372 @default.
• W2796758701 cites W2140245639 @default.
• W2796758701 cites W2145094598 @default.
• W2796758701 cites W2160547390 @default.
• W2796758701 cites W2162221686 @default.
• W2796758701 cites W2163112044 @default.
• W2796758701 cites W2163398148 @default.
• W2796758701 cites W2164585733 @default.
• W2796758701 cites W2184852195 @default.
• W2796758701 cites W2194775991 @default.
• W2796758701 cites W2198221632 @default.
• W2796758701 cites W2292992741 @default.
• W2796758701 cites W2293597654 @default.
• W2796758701 cites W2296616510 @default.
• W2796758701 cites W2315814222 @default.
• W2796758701 cites W2331501241 @default.
• W2796758701 cites W2401664211 @default.
• W2796758701 cites W2422804631 @default.
• W2796758701 cites W2466611277 @default.
• W2796758701 cites W2549916392 @default.
• W2796758701 cites W2584565348 @default.
• W2796758701 cites W2626739722 @default.
• W2796758701 cites W2741587712 @default.
• W2796758701 cites W2795467458 @default.
• W2796758701 cites W2797628751 @default.
• W2796758701 cites W2889134685 @default.
• W2796758701 cites W2890129614 @default.
• W2796758701 cites W2902083850 @default.
• W2796758701 cites W2907946893 @default.
• W2796758701 cites W2963103976 @default.
• W2796758701 cites W2963542991 @default.
• W2796758701 cites W2964074409 @default.
• W2796758701 cites W3118608800 @default.
• W2796758701 doi "https://doi.org/10.48550/arxiv.1804.05515" @default.
• W2796758701 hasPublicationYear "2018" @default.
• W2796758701 type Work @default.
• W2796758701 sameAs 2796758701 @default.
• W2796758701 citedByCount "3" @default.
• W2796758701 countsByYear W27967587012018 @default.
• W2796758701 crossrefType "posted-content" @default.
• W2796758701 hasAuthorship W2796758701A5033755969 @default.
• W2796758701 hasAuthorship W2796758701A5048522863 @default.
• W2796758701 hasAuthorship W2796758701A5049225160 @default.
• W2796758701 hasAuthorship W2796758701A5069376593 @default.
• W2796758701 hasAuthorship W2796758701A5086939495 @default.
• W2796758701 hasBestOaLocation W27967587011 @default.
• W2796758701 hasConcept C104317684 @default.
• W2796758701 hasConcept C105795698 @default.
• W2796758701 hasConcept C111919701 @default.
• W2796758701 hasConcept C11413529 @default.
• W2796758701 hasConcept C119857082 @default.
• W2796758701 hasConcept C138885662 @default.
• W2796758701 hasConcept C153180895 @default.
• W2796758701 hasConcept C154945302 @default.
• W2796758701 hasConcept C179518139 @default.
• W2796758701 hasConcept C185592680 @default.
• W2796758701 hasConcept C2776214188 @default.
• W2796758701 hasConcept C2776401178 @default.
• W2796758701 hasConcept C33923547 @default.
• W2796758701 hasConcept C41008148 @default.
• W2796758701 hasConcept C41895202 @default.
• W2796758701 hasConcept C43126263 @default.
• W2796758701 hasConcept C55493867 @default.

• next