Matches in SemOpenAlex for { <https://semopenalex.org/work/W89788180> ?p ?o ?g. }
- W89788180 endingPage "1417" @default.
- W89788180 startingPage "1409" @default.
- W89788180 abstract "In this study, we derive algorithms for estimating mixed β-divergences. Such cost functions are useful for Nonnegative Matrix and Tensor Factorization models with a compound Poisson observation model. Compound Poisson is a particular Tweedie model, an important special case of exponential dispersion models characterized by the fact that the variance is proportional to a power function of the mean. There are several well known matrix and tensor factorization algorithms that minimize the β-divergence; these estimate the mean parameter. The probabilistic interpretation gives us more exibility and robustness by providing us additional tunable parameters such as power and dispersion. Estimation of the power parameter is useful for choosing a suitable divergence and estimation of dispersion is useful for data driven regularization and weighting in collective/coupled factorization of heterogeneous datasets. We present three inference algorithms for both estimating the factors and the additional parameters of the compound Poisson distribution. The methods are evaluated on two applications: modeling symbolic representations for polyphonic music and lyric prediction from audio features. Our conclusion is that the compound poisson based factorization models can be useful for sparse positive data." @default.
- W89788180 created "2016-06-24" @default.
- W89788180 creator A5045915674 @default.
- W89788180 creator A5053326908 @default.
- W89788180 creator A5064633247 @default.
- W89788180 date "2013-06-16" @default.
- W89788180 modified "2023-09-27" @default.
- W89788180 title "Learning the beta-Divergence in Tweedie Compound Poisson Matrix Factorization Models" @default.
- W89788180 cites W1246381107 @default.
- W89788180 cites W1528905581 @default.
- W89788180 cites W1556219185 @default.
- W89788180 cites W1819710477 @default.
- W89788180 cites W1930148948 @default.
- W89788180 cites W1963628156 @default.
- W89788180 cites W1983819898 @default.
- W89788180 cites W2035484822 @default.
- W89788180 cites W2039844283 @default.
- W89788180 cites W2059586969 @default.
- W89788180 cites W2104298926 @default.
- W89788180 cites W2106582496 @default.
- W89788180 cites W2110007838 @default.
- W89788180 cites W2130295778 @default.
- W89788180 cites W2147574125 @default.
- W89788180 cites W2155731523 @default.
- W89788180 cites W2404400936 @default.
- W89788180 cites W65622836 @default.
- W89788180 hasPublicationYear "2013" @default.
- W89788180 type Work @default.
- W89788180 sameAs 89788180 @default.
- W89788180 citedByCount "11" @default.
- W89788180 countsByYear W897881802014 @default.
- W89788180 countsByYear W897881802015 @default.
- W89788180 countsByYear W897881802016 @default.
- W89788180 countsByYear W897881802017 @default.
- W89788180 countsByYear W897881802019 @default.
- W89788180 countsByYear W897881802020 @default.
- W89788180 crossrefType "proceedings-article" @default.
- W89788180 hasAuthorship W89788180A5045915674 @default.
- W89788180 hasAuthorship W89788180A5053326908 @default.
- W89788180 hasAuthorship W89788180A5064633247 @default.
- W89788180 hasConcept C100906024 @default.
- W89788180 hasConcept C105795698 @default.
- W89788180 hasConcept C11413529 @default.
- W89788180 hasConcept C121332964 @default.
- W89788180 hasConcept C126255220 @default.
- W89788180 hasConcept C152671427 @default.
- W89788180 hasConcept C158693339 @default.
- W89788180 hasConcept C185429906 @default.
- W89788180 hasConcept C187834632 @default.
- W89788180 hasConcept C28826006 @default.
- W89788180 hasConcept C33923547 @default.
- W89788180 hasConcept C39482219 @default.
- W89788180 hasConcept C41008148 @default.
- W89788180 hasConcept C42355184 @default.
- W89788180 hasConcept C46030957 @default.
- W89788180 hasConcept C62520636 @default.
- W89788180 hasConceptScore W89788180C100906024 @default.
- W89788180 hasConceptScore W89788180C105795698 @default.
- W89788180 hasConceptScore W89788180C11413529 @default.
- W89788180 hasConceptScore W89788180C121332964 @default.
- W89788180 hasConceptScore W89788180C126255220 @default.
- W89788180 hasConceptScore W89788180C152671427 @default.
- W89788180 hasConceptScore W89788180C158693339 @default.
- W89788180 hasConceptScore W89788180C185429906 @default.
- W89788180 hasConceptScore W89788180C187834632 @default.
- W89788180 hasConceptScore W89788180C28826006 @default.
- W89788180 hasConceptScore W89788180C33923547 @default.
- W89788180 hasConceptScore W89788180C39482219 @default.
- W89788180 hasConceptScore W89788180C41008148 @default.
- W89788180 hasConceptScore W89788180C42355184 @default.
- W89788180 hasConceptScore W89788180C46030957 @default.
- W89788180 hasConceptScore W89788180C62520636 @default.
- W89788180 hasLocation W897881801 @default.
- W89788180 hasOpenAccess W89788180 @default.
- W89788180 hasPrimaryLocation W897881801 @default.
- W89788180 hasRelatedWork W1585549083 @default.
- W89788180 hasRelatedWork W1902027874 @default.
- W89788180 hasRelatedWork W1983819898 @default.
- W89788180 hasRelatedWork W1986966428 @default.
- W89788180 hasRelatedWork W2031696998 @default.
- W89788180 hasRelatedWork W2039844283 @default.
- W89788180 hasRelatedWork W2049459260 @default.
- W89788180 hasRelatedWork W2106961326 @default.
- W89788180 hasRelatedWork W2114508388 @default.
- W89788180 hasRelatedWork W2116059156 @default.
- W89788180 hasRelatedWork W2116542188 @default.
- W89788180 hasRelatedWork W2147574125 @default.
- W89788180 hasRelatedWork W2403286959 @default.
- W89788180 hasRelatedWork W2963256666 @default.
- W89788180 hasRelatedWork W2970592101 @default.
- W89788180 hasRelatedWork W2980288697 @default.
- W89788180 hasRelatedWork W3014232082 @default.
- W89788180 hasRelatedWork W3038413610 @default.
- W89788180 hasRelatedWork W3143596294 @default.
- W89788180 hasRelatedWork W343470769 @default.
- W89788180 isParatext "false" @default.
- W89788180 isRetracted "false" @default.
- W89788180 magId "89788180" @default.