Matches in SemOpenAlex for { <https://semopenalex.org/work/W2339443313> ?p ?o ?g. }
- W2339443313 abstract "Latent factor models are the canonical statistical tool for exploratory analyses of low-dimensional linear structure for an observation matrix with p features across n samples. We develop a structured Bayesian group factor analysis model that extends the factor model to multiple coupled observation matrices; in the case of two observations, this reduces to a Bayesian model of canonical correlation analysis. The main contribution of this work is to carefully define a structured Bayesian prior that encourages both element-wise and column-wise shrinkage and leads to desirable behavior on high-dimensional data. In particular, our model puts a structured prior on the joint factor loading matrix, regularizing at three levels, which enables element-wise sparsity and unsupervised recovery of latent factors corresponding to structured variance across arbitrary subsets of the observations. In addition, our structured prior allows for both dense and sparse latent factors so that covariation among either all features or only a subset of features can both be recovered. We use fast parameter-expanded expectation-maximization for parameter estimation in this model. We validate our method on both simulated data with substantial structure and real data, comparing against a number of state-of-the-art approaches. These results illustrate useful properties of our model, including i) recovering sparse signal in the presence of dense effects; ii) the ability to scale naturally to large numbers of observations; iii) flexible observation- and factor-specific regularization to recover factors with a wide variety of sparsity levels and percentage of variance explained; and iv) tractable inference that scales to modern genomic and document data sizes." @default.
- W2339443313 created "2016-06-24" @default.
- W2339443313 creator A5008602595 @default.
- W2339443313 creator A5036208626 @default.
- W2339443313 creator A5058822190 @default.
- W2339443313 creator A5065136437 @default.
- W2339443313 date "2014-11-11" @default.
- W2339443313 modified "2023-09-25" @default.
- W2339443313 title "Bayesian group latent factor analysis with structured sparsity" @default.
- W2339443313 cites W1493404174 @default.
- W2339443313 cites W1494413412 @default.
- W2339443313 cites W1511986666 @default.
- W2339443313 cites W1532737361 @default.
- W2339443313 cites W1545687120 @default.
- W2339443313 cites W1567512734 @default.
- W2339443313 cites W1575567117 @default.
- W2339443313 cites W1592941960 @default.
- W2339443313 cites W1604799237 @default.
- W2339443313 cites W1648445109 @default.
- W2339443313 cites W1814082361 @default.
- W2339443313 cites W1880944740 @default.
- W2339443313 cites W1898436635 @default.
- W2339443313 cites W1967827763 @default.
- W2339443313 cites W1968244248 @default.
- W2339443313 cites W1974611538 @default.
- W2339443313 cites W1975900269 @default.
- W2339443313 cites W1976365540 @default.
- W2339443313 cites W1982652137 @default.
- W2339443313 cites W1985629708 @default.
- W2339443313 cites W1998966727 @default.
- W2339443313 cites W2020082133 @default.
- W2339443313 cites W2022821295 @default.
- W2339443313 cites W2025341678 @default.
- W2339443313 cites W2033765726 @default.
- W2339443313 cites W2040854171 @default.
- W2339443313 cites W2041779820 @default.
- W2339443313 cites W2047028564 @default.
- W2339443313 cites W2049633694 @default.
- W2339443313 cites W2052637985 @default.
- W2339443313 cites W2053609837 @default.
- W2339443313 cites W2054110507 @default.
- W2339443313 cites W2056165766 @default.
- W2339443313 cites W2072460814 @default.
- W2339443313 cites W2073911885 @default.
- W2339443313 cites W2078803352 @default.
- W2339443313 cites W2081385752 @default.
- W2339443313 cites W2085459418 @default.
- W2339443313 cites W2086953401 @default.
- W2339443313 cites W2087101057 @default.
- W2339443313 cites W2092334563 @default.
- W2339443313 cites W2096152098 @default.
- W2339443313 cites W2098143048 @default.
- W2339443313 cites W2099741732 @default.
- W2339443313 cites W2101234009 @default.
- W2339443313 cites W2102701235 @default.
- W2339443313 cites W2103510282 @default.
- W2339443313 cites W2106966651 @default.
- W2339443313 cites W2108687351 @default.
- W2339443313 cites W2114169935 @default.
- W2339443313 cites W2117988331 @default.
- W2339443313 cites W2117994680 @default.
- W2339443313 cites W2122825543 @default.
- W2339443313 cites W2125290066 @default.
- W2339443313 cites W2126497681 @default.
- W2339443313 cites W2130186565 @default.
- W2339443313 cites W2130336429 @default.
- W2339443313 cites W2135046866 @default.
- W2339443313 cites W2135194391 @default.
- W2339443313 cites W2136111243 @default.
- W2339443313 cites W2139845570 @default.
- W2339443313 cites W2141986476 @default.
- W2339443313 cites W2145863175 @default.
- W2339443313 cites W2145962650 @default.
- W2339443313 cites W2146610201 @default.
- W2339443313 cites W2151544098 @default.
- W2339443313 cites W2155085787 @default.
- W2339443313 cites W2156872152 @default.
- W2339443313 cites W2157752701 @default.
- W2339443313 cites W2157801062 @default.
- W2339443313 cites W2158217645 @default.
- W2339443313 cites W2162315509 @default.
- W2339443313 cites W2168796889 @default.
- W2339443313 cites W2497431972 @default.
- W2339443313 cites W2509600984 @default.
- W2339443313 cites W2514253892 @default.
- W2339443313 cites W2951741291 @default.
- W2339443313 cites W2952132522 @default.
- W2339443313 cites W3104624268 @default.
- W2339443313 cites W2163948609 @default.
- W2339443313 hasPublicationYear "2014" @default.
- W2339443313 type Work @default.
- W2339443313 sameAs 2339443313 @default.
- W2339443313 citedByCount "3" @default.
- W2339443313 countsByYear W23394433132015 @default.
- W2339443313 countsByYear W23394433132016 @default.
- W2339443313 crossrefType "posted-content" @default.
- W2339443313 hasAuthorship W2339443313A5008602595 @default.
- W2339443313 hasAuthorship W2339443313A5036208626 @default.
- W2339443313 hasAuthorship W2339443313A5058822190 @default.
- W2339443313 hasAuthorship W2339443313A5065136437 @default.