Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319984003> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4319984003 abstract "In many Bayesian computations, we first obtain the expression of the joint distribution of all the unknown variables given the observed data. In general, this expression is not separable in those variables. Thus, obtaining the marginals for each variable and computing the expectations is difficult and costly. This problem becomes even more difficult in high dimensional quandaries, which is an important issue in inverse problems. We may then try to propose a surrogate expression with which we can carry out approximate computations. Often, a separable expression approximation can be useful enough. The variational Bayesian approximation (VBA) is a technique that approximates the joint distribution p with an easier, for example separable, distribution q by minimizing the Kullback–Leibler divergence KL(q|p). When q is separable in all the variables, the approximation is also called the mean field approximation (MFA), and so q is the product of the approximated marginals. A first standard and general algorithm is the alternate optimization of KL(q|p) with respect to qi. A second general approach is its optimization in the Riemannian manifold. However, in this paper, for practical reasons, we consider the case where p is in the exponential family and so is q. For this case, KL(q|p) becomes a function of the parameters θ of the exponential family. Then, we can use any other optimization algorithm to obtain those parameters. In this paper, we compare three optimization algorithms, namely a standard alternate optimization, a gradient-based algorithm and a natural gradient algorithm, and study their relative performances in three examples." @default.
- W4319984003 created "2023-02-11" @default.
- W4319984003 creator A5034210308 @default.
- W4319984003 creator A5061234480 @default.
- W4319984003 date "2023-02-08" @default.
- W4319984003 modified "2023-09-30" @default.
- W4319984003 title "Variational Bayesian Approximation (VBA): A Comparison between Three Optimization Algorithms" @default.
- W4319984003 cites W1965555277 @default.
- W4319984003 cites W1986411099 @default.
- W4319984003 cites W2032183568 @default.
- W4319984003 cites W2108095822 @default.
- W4319984003 cites W2136634080 @default.
- W4319984003 cites W2138598313 @default.
- W4319984003 cites W2167270514 @default.
- W4319984003 cites W4301359222 @default.
- W4319984003 doi "https://doi.org/10.3390/psf2022005048" @default.
- W4319984003 hasPublicationYear "2023" @default.
- W4319984003 type Work @default.
- W4319984003 citedByCount "0" @default.
- W4319984003 crossrefType "proceedings-article" @default.
- W4319984003 hasAuthorship W4319984003A5034210308 @default.
- W4319984003 hasAuthorship W4319984003A5061234480 @default.
- W4319984003 hasBestOaLocation W43199840031 @default.
- W4319984003 hasConcept C11413529 @default.
- W4319984003 hasConcept C126255220 @default.
- W4319984003 hasConcept C134306372 @default.
- W4319984003 hasConcept C137836250 @default.
- W4319984003 hasConcept C138885662 @default.
- W4319984003 hasConcept C148764684 @default.
- W4319984003 hasConcept C207390915 @default.
- W4319984003 hasConcept C28826006 @default.
- W4319984003 hasConcept C33923547 @default.
- W4319984003 hasConcept C41008148 @default.
- W4319984003 hasConcept C41895202 @default.
- W4319984003 hasConcept C45374587 @default.
- W4319984003 hasConcept C70710897 @default.
- W4319984003 hasConceptScore W4319984003C11413529 @default.
- W4319984003 hasConceptScore W4319984003C126255220 @default.
- W4319984003 hasConceptScore W4319984003C134306372 @default.
- W4319984003 hasConceptScore W4319984003C137836250 @default.
- W4319984003 hasConceptScore W4319984003C138885662 @default.
- W4319984003 hasConceptScore W4319984003C148764684 @default.
- W4319984003 hasConceptScore W4319984003C207390915 @default.
- W4319984003 hasConceptScore W4319984003C28826006 @default.
- W4319984003 hasConceptScore W4319984003C33923547 @default.
- W4319984003 hasConceptScore W4319984003C41008148 @default.
- W4319984003 hasConceptScore W4319984003C41895202 @default.
- W4319984003 hasConceptScore W4319984003C45374587 @default.
- W4319984003 hasConceptScore W4319984003C70710897 @default.
- W4319984003 hasLocation W43199840031 @default.
- W4319984003 hasOpenAccess W4319984003 @default.
- W4319984003 hasPrimaryLocation W43199840031 @default.
- W4319984003 hasRelatedWork W1534878884 @default.
- W4319984003 hasRelatedWork W1580435510 @default.
- W4319984003 hasRelatedWork W1971514761 @default.
- W4319984003 hasRelatedWork W1985684185 @default.
- W4319984003 hasRelatedWork W2024975317 @default.
- W4319984003 hasRelatedWork W2112143158 @default.
- W4319984003 hasRelatedWork W2377278556 @default.
- W4319984003 hasRelatedWork W2384148574 @default.
- W4319984003 hasRelatedWork W2991431918 @default.
- W4319984003 hasRelatedWork W64105819 @default.
- W4319984003 isParatext "false" @default.
- W4319984003 isRetracted "false" @default.
- W4319984003 workType "article" @default.