FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951064181> ?p ?o ?g. }

• W2951064181 abstract "Many modern tools in machine learning and signal processing, such as sparse dictionary learning, principal component analysis (PCA), non-negative matrix factorization (NMF), $K$-means clustering, etc., rely on the factorization of a matrix obtained by concatenating high-dimensional vectors from a training collection. While the idealized task would be to optimize the expected quality of the factors over the underlying distribution of training vectors, it is achieved in practice by minimizing an empirical average over the considered collection. The focus of this paper is to provide sample complexity estimates to uniformly control how much the empirical average deviates from the expected cost function. Standard arguments imply that the performance of the empirical predictor also exhibit such guarantees. The level of genericity of the approach encompasses several possible constraints on the factors (tensor product structure, shift-invariance, sparsity ldots), thus providing a unified perspective on the sample complexity of several widely used matrix factorization schemes. The derived generalization bounds behave proportional to $sqrt{log(n)/n}$ w.r.t. the number of samples $n$ for the considered matrix factorization techniques." @default.
• W2951064181 created "2019-06-27" @default.
• W2951064181 creator A5001483226 @default.
• W2951064181 creator A5033851429 @default.
• W2951064181 creator A5041230403 @default.
• W2951064181 creator A5055847035 @default.
• W2951064181 creator A5065943708 @default.
• W2951064181 date "2013-12-13" @default.
• W2951064181 modified "2023-09-27" @default.
• W2951064181 title "Sample Complexity of Dictionary Learning and other Matrix Factorizations" @default.
• W2951064181 cites W1482235099 @default.
• W2951064181 cites W1539012881 @default.
• W2951064181 cites W1634005169 @default.
• W2951064181 cites W18355306 @default.
• W2951064181 cites W1963826206 @default.
• W2951064181 cites W1999174140 @default.
• W2951064181 cites W2004544971 @default.
• W2951064181 cites W2008740515 @default.
• W2951064181 cites W2013912476 @default.
• W2951064181 cites W2045512849 @default.
• W2951064181 cites W2047278710 @default.
• W2951064181 cites W2050744541 @default.
• W2951064181 cites W2052044664 @default.
• W2951064181 cites W2091475238 @default.
• W2951064181 cites W2098290597 @default.
• W2951064181 cites W2099321050 @default.
• W2951064181 cites W2105464873 @default.
• W2951064181 cites W2108687351 @default.
• W2951064181 cites W2109999391 @default.
• W2951064181 cites W2110323469 @default.
• W2951064181 cites W2111187851 @default.
• W2951064181 cites W2112447569 @default.
• W2951064181 cites W2114609025 @default.
• W2951064181 cites W2115429828 @default.
• W2951064181 cites W2115755118 @default.
• W2951064181 cites W2124623336 @default.
• W2951064181 cites W2131172946 @default.
• W2951064181 cites W2137216203 @default.
• W2951064181 cites W2139095575 @default.
• W2951064181 cites W2142766915 @default.
• W2951064181 cites W2142940228 @default.
• W2951064181 cites W2145096794 @default.
• W2951064181 cites W2156117587 @default.
• W2951064181 cites W2160547390 @default.
• W2951064181 cites W2161065057 @default.
• W2951064181 cites W2163398148 @default.
• W2951064181 cites W2167349346 @default.
• W2951064181 cites W2296319761 @default.
• W2951064181 cites W2296399167 @default.
• W2951064181 cites W2949672605 @default.
• W2951064181 cites W2950289646 @default.
• W2951064181 cites W2963641291 @default.
• W2951064181 cites W3143596294 @default.
• W2951064181 hasPublicationYear "2013" @default.
• W2951064181 type Work @default.
• W2951064181 sameAs 2951064181 @default.
• W2951064181 citedByCount "6" @default.
• W2951064181 countsByYear W29510641812014 @default.
• W2951064181 countsByYear W29510641812015 @default.
• W2951064181 countsByYear W29510641812016 @default.
• W2951064181 crossrefType "posted-content" @default.
• W2951064181 hasAuthorship W2951064181A5001483226 @default.
• W2951064181 hasAuthorship W2951064181A5033851429 @default.
• W2951064181 hasAuthorship W2951064181A5041230403 @default.
• W2951064181 hasAuthorship W2951064181A5055847035 @default.
• W2951064181 hasAuthorship W2951064181A5065943708 @default.
• W2951064181 hasConcept C106487976 @default.
• W2951064181 hasConcept C11413529 @default.
• W2951064181 hasConcept C121332964 @default.
• W2951064181 hasConcept C12713177 @default.
• W2951064181 hasConcept C134306372 @default.
• W2951064181 hasConcept C14036430 @default.
• W2951064181 hasConcept C152671427 @default.
• W2951064181 hasConcept C154945302 @default.
• W2951064181 hasConcept C155281189 @default.
• W2951064181 hasConcept C158693339 @default.
• W2951064181 hasConcept C159985019 @default.
• W2951064181 hasConcept C177148314 @default.
• W2951064181 hasConcept C185592680 @default.
• W2951064181 hasConcept C187834632 @default.
• W2951064181 hasConcept C192562407 @default.
• W2951064181 hasConcept C198531522 @default.
• W2951064181 hasConcept C202444582 @default.
• W2951064181 hasConcept C27438332 @default.
• W2951064181 hasConcept C33923547 @default.
• W2951064181 hasConcept C41008148 @default.
• W2951064181 hasConcept C42355184 @default.
• W2951064181 hasConcept C43617362 @default.
• W2951064181 hasConcept C62520636 @default.
• W2951064181 hasConcept C73555534 @default.
• W2951064181 hasConcept C78458016 @default.
• W2951064181 hasConcept C86803240 @default.
• W2951064181 hasConceptScore W2951064181C106487976 @default.
• W2951064181 hasConceptScore W2951064181C11413529 @default.
• W2951064181 hasConceptScore W2951064181C121332964 @default.
• W2951064181 hasConceptScore W2951064181C12713177 @default.
• W2951064181 hasConceptScore W2951064181C134306372 @default.
• W2951064181 hasConceptScore W2951064181C14036430 @default.
• W2951064181 hasConceptScore W2951064181C152671427 @default.
• W2951064181 hasConceptScore W2951064181C154945302 @default.

• next