Matches in SemOpenAlex for { <https://semopenalex.org/work/W1591701846> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W1591701846 abstract "We investigate the optimal kernel for sample-based model selection in unsupervised learning if maximum likelihood approaches are intractable. Given a set of training data and a set of data generated by the model, two kernel density estimators are constructed. A model is selected through gradient descent w.r.t. the model parameters on the integrated squared difference between the density estimators. Firstly we prove that convergence is optimal, i.e. that the cost function has only one global minimum w.r.t. the locations of the model samples, if and only if the kernel in the reparametrized cost function is a Coulomb kernel. As a consequence, Gaussian kernels commonly used for density estimators are suboptimal. Secondly we show that the absolute value of the difference between model and reference density converges at least with 1/t. Finally, we apply the new methods to distribution free ICA and to nonlinear ICA." @default.
- W1591701846 created "2016-06-24" @default.
- W1591701846 creator A5053148274 @default.
- W1591701846 creator A5073910479 @default.
- W1591701846 date "2006-01-05" @default.
- W1591701846 modified "2023-10-18" @default.
- W1591701846 title "Optimal kernels for unsupervised learning" @default.
- W1591701846 cites W1547224907 @default.
- W1591701846 cites W2009479673 @default.
- W1591701846 cites W2066306397 @default.
- W1591701846 cites W2108384452 @default.
- W1591701846 cites W2119667862 @default.
- W1591701846 cites W2124757684 @default.
- W1591701846 cites W2139896607 @default.
- W1591701846 cites W2166698530 @default.
- W1591701846 doi "https://doi.org/10.1109/ijcnn.2005.1556169" @default.
- W1591701846 hasPublicationYear "2006" @default.
- W1591701846 type Work @default.
- W1591701846 sameAs 1591701846 @default.
- W1591701846 citedByCount "3" @default.
- W1591701846 countsByYear W15917018462017 @default.
- W1591701846 countsByYear W15917018462018 @default.
- W1591701846 countsByYear W15917018462020 @default.
- W1591701846 crossrefType "proceedings-article" @default.
- W1591701846 hasAuthorship W1591701846A5053148274 @default.
- W1591701846 hasAuthorship W1591701846A5073910479 @default.
- W1591701846 hasConcept C105795698 @default.
- W1591701846 hasConcept C114614502 @default.
- W1591701846 hasConcept C121332964 @default.
- W1591701846 hasConcept C122280245 @default.
- W1591701846 hasConcept C12267149 @default.
- W1591701846 hasConcept C126255220 @default.
- W1591701846 hasConcept C154945302 @default.
- W1591701846 hasConcept C162324750 @default.
- W1591701846 hasConcept C163716315 @default.
- W1591701846 hasConcept C185429906 @default.
- W1591701846 hasConcept C189508267 @default.
- W1591701846 hasConcept C195699287 @default.
- W1591701846 hasConcept C197055811 @default.
- W1591701846 hasConcept C2777303404 @default.
- W1591701846 hasConcept C28826006 @default.
- W1591701846 hasConcept C33923547 @default.
- W1591701846 hasConcept C41008148 @default.
- W1591701846 hasConcept C50522688 @default.
- W1591701846 hasConcept C62520636 @default.
- W1591701846 hasConcept C71134354 @default.
- W1591701846 hasConcept C7218915 @default.
- W1591701846 hasConcept C74193536 @default.
- W1591701846 hasConcept C93959086 @default.
- W1591701846 hasConceptScore W1591701846C105795698 @default.
- W1591701846 hasConceptScore W1591701846C114614502 @default.
- W1591701846 hasConceptScore W1591701846C121332964 @default.
- W1591701846 hasConceptScore W1591701846C122280245 @default.
- W1591701846 hasConceptScore W1591701846C12267149 @default.
- W1591701846 hasConceptScore W1591701846C126255220 @default.
- W1591701846 hasConceptScore W1591701846C154945302 @default.
- W1591701846 hasConceptScore W1591701846C162324750 @default.
- W1591701846 hasConceptScore W1591701846C163716315 @default.
- W1591701846 hasConceptScore W1591701846C185429906 @default.
- W1591701846 hasConceptScore W1591701846C189508267 @default.
- W1591701846 hasConceptScore W1591701846C195699287 @default.
- W1591701846 hasConceptScore W1591701846C197055811 @default.
- W1591701846 hasConceptScore W1591701846C2777303404 @default.
- W1591701846 hasConceptScore W1591701846C28826006 @default.
- W1591701846 hasConceptScore W1591701846C33923547 @default.
- W1591701846 hasConceptScore W1591701846C41008148 @default.
- W1591701846 hasConceptScore W1591701846C50522688 @default.
- W1591701846 hasConceptScore W1591701846C62520636 @default.
- W1591701846 hasConceptScore W1591701846C71134354 @default.
- W1591701846 hasConceptScore W1591701846C7218915 @default.
- W1591701846 hasConceptScore W1591701846C74193536 @default.
- W1591701846 hasConceptScore W1591701846C93959086 @default.
- W1591701846 hasLocation W15917018461 @default.
- W1591701846 hasOpenAccess W1591701846 @default.
- W1591701846 hasPrimaryLocation W15917018461 @default.
- W1591701846 hasRelatedWork W1565487582 @default.
- W1591701846 hasRelatedWork W1973028026 @default.
- W1591701846 hasRelatedWork W1974314970 @default.
- W1591701846 hasRelatedWork W1975302268 @default.
- W1591701846 hasRelatedWork W1996273825 @default.
- W1591701846 hasRelatedWork W2011689144 @default.
- W1591701846 hasRelatedWork W2082050365 @default.
- W1591701846 hasRelatedWork W2089376820 @default.
- W1591701846 hasRelatedWork W2100303126 @default.
- W1591701846 hasRelatedWork W2123168458 @default.
- W1591701846 hasRelatedWork W2135144860 @default.
- W1591701846 hasRelatedWork W2139404963 @default.
- W1591701846 hasRelatedWork W2146433171 @default.
- W1591701846 hasRelatedWork W2378099159 @default.
- W1591701846 hasRelatedWork W265163128 @default.
- W1591701846 hasRelatedWork W3100501601 @default.
- W1591701846 hasRelatedWork W3123705593 @default.
- W1591701846 hasRelatedWork W38231399 @default.
- W1591701846 hasRelatedWork W629575809 @default.
- W1591701846 hasRelatedWork W824181752 @default.
- W1591701846 isParatext "false" @default.
- W1591701846 isRetracted "false" @default.
- W1591701846 magId "1591701846" @default.
- W1591701846 workType "article" @default.