Matches in SemOpenAlex for { <https://semopenalex.org/work/W18355306> ?p ?o ?g. }
- W18355306 abstract "A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only been a few theoretical arguments supporting these evidences. In particular, sparse coding, or sparse dictionary learning, relies on a non-convex procedure whose local minima have not been fully analyzed yet. In this paper, we consider a probabilistic model of sparse signals, and show that, with high probability, sparse coding admits a local minimum around the reference dictionary generating the signals. Our study takes into account the case of over-complete dictionaries and noisy signals, thus extending previous work limited to noiseless settings and/or under-complete dictionaries. The analysis we conduct is non-asymptotic and makes it possible to understand how the key quantities of the problem, such as the coherence or the level of noise, can scale with respect to the dimension of the signals, the number of atoms, the sparsity and the number of observations." @default.
- W18355306 created "2016-06-24" @default.
- W18355306 creator A5001483226 @default.
- W18355306 creator A5033851429 @default.
- W18355306 creator A5041230403 @default.
- W18355306 date "2012-10-01" @default.
- W18355306 modified "2023-10-16" @default.
- W18355306 title "Local stability and robustness of sparse dictionary learning in the presence of noise" @default.
- W18355306 cites W1482235099 @default.
- W18355306 cites W1484382611 @default.
- W18355306 cites W1495162547 @default.
- W18355306 cites W1539012881 @default.
- W18355306 cites W1544839292 @default.
- W18355306 cites W1674879387 @default.
- W18355306 cites W1755563775 @default.
- W18355306 cites W1804110266 @default.
- W18355306 cites W1969415786 @default.
- W18355306 cites W1986931325 @default.
- W18355306 cites W2047278710 @default.
- W18355306 cites W2093545205 @default.
- W18355306 cites W2099641086 @default.
- W18355306 cites W2105464873 @default.
- W18355306 cites W2112447569 @default.
- W18355306 cites W2115755118 @default.
- W18355306 cites W2116148865 @default.
- W18355306 cites W2127114523 @default.
- W18355306 cites W2127300249 @default.
- W18355306 cites W2135046866 @default.
- W18355306 cites W2140433132 @default.
- W18355306 cites W2141552007 @default.
- W18355306 cites W2149206122 @default.
- W18355306 cites W2150940164 @default.
- W18355306 cites W2167349346 @default.
- W18355306 cites W2170091909 @default.
- W18355306 cites W2170402521 @default.
- W18355306 cites W2222512263 @default.
- W18355306 cites W2610857016 @default.
- W18355306 cites W2797638056 @default.
- W18355306 cites W2913586401 @default.
- W18355306 cites W2953214153 @default.
- W18355306 cites W2963641291 @default.
- W18355306 cites W2965497096 @default.
- W18355306 cites W3100456593 @default.
- W18355306 cites W3101762025 @default.
- W18355306 cites W3104148512 @default.
- W18355306 hasPublicationYear "2012" @default.
- W18355306 type Work @default.
- W18355306 sameAs 18355306 @default.
- W18355306 citedByCount "17" @default.
- W18355306 countsByYear W183553062013 @default.
- W18355306 countsByYear W183553062014 @default.
- W18355306 countsByYear W183553062015 @default.
- W18355306 countsByYear W183553062017 @default.
- W18355306 countsByYear W183553062019 @default.
- W18355306 countsByYear W183553062020 @default.
- W18355306 crossrefType "report" @default.
- W18355306 hasAuthorship W18355306A5001483226 @default.
- W18355306 hasAuthorship W18355306A5033851429 @default.
- W18355306 hasAuthorship W18355306A5041230403 @default.
- W18355306 hasBestOaLocation W183553061 @default.
- W18355306 hasConcept C104317684 @default.
- W18355306 hasConcept C112972136 @default.
- W18355306 hasConcept C119857082 @default.
- W18355306 hasConcept C124066611 @default.
- W18355306 hasConcept C153180895 @default.
- W18355306 hasConcept C154945302 @default.
- W18355306 hasConcept C185592680 @default.
- W18355306 hasConcept C28490314 @default.
- W18355306 hasConcept C2988886741 @default.
- W18355306 hasConcept C41008148 @default.
- W18355306 hasConcept C55493867 @default.
- W18355306 hasConcept C63479239 @default.
- W18355306 hasConceptScore W18355306C104317684 @default.
- W18355306 hasConceptScore W18355306C112972136 @default.
- W18355306 hasConceptScore W18355306C119857082 @default.
- W18355306 hasConceptScore W18355306C124066611 @default.
- W18355306 hasConceptScore W18355306C153180895 @default.
- W18355306 hasConceptScore W18355306C154945302 @default.
- W18355306 hasConceptScore W18355306C185592680 @default.
- W18355306 hasConceptScore W18355306C28490314 @default.
- W18355306 hasConceptScore W18355306C2988886741 @default.
- W18355306 hasConceptScore W18355306C41008148 @default.
- W18355306 hasConceptScore W18355306C55493867 @default.
- W18355306 hasConceptScore W18355306C63479239 @default.
- W18355306 hasLocation W183553061 @default.
- W18355306 hasLocation W183553062 @default.
- W18355306 hasLocation W183553063 @default.
- W18355306 hasOpenAccess W18355306 @default.
- W18355306 hasPrimaryLocation W183553061 @default.
- W18355306 hasRelatedWork W2961085424 @default.
- W18355306 hasRelatedWork W3046775127 @default.
- W18355306 hasRelatedWork W3170094116 @default.
- W18355306 hasRelatedWork W4205958290 @default.
- W18355306 hasRelatedWork W4285260836 @default.
- W18355306 hasRelatedWork W4286629047 @default.
- W18355306 hasRelatedWork W4306321456 @default.
- W18355306 hasRelatedWork W4306674287 @default.
- W18355306 hasRelatedWork W4386462264 @default.
- W18355306 hasRelatedWork W4224009465 @default.
- W18355306 isParatext "false" @default.