Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159719175> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3159719175 endingPage "2457" @default.
- W3159719175 startingPage "2449" @default.
- W3159719175 abstract "Transformation-based methods have been an attractive approach in non-parametric inference for problems such as unconditional and conditional density estimation due to their unique hierarchical structure that models the data as flexible transformation of a set of common latent variables. More recently, transformation-based models have been used in variational inference (VI) to construct flexible implicit families of variational distributions. However, their use in both non-parametric inference and variational inference lacks theoretical justification. We provide theoretical justification for the use of non-linear latent variable models (NL-LVMs) in non-parametric inference by showing that the support of the transformation induced prior in the space of densities is sufficiently large in the $L_1$ sense. We also show that, when a Gaussian process (GP) prior is placed on the transformation function, the posterior concentrates at the optimal rate up to a logarithmic factor. Adopting the flexibility demonstrated in the non-parametric setting, we use the NL-LVM to construct an implicit family of variational distributions, deemed GP-IVI. We delineate sufficient conditions under which GP-IVI achieves optimal risk bounds and approximates the true posterior in the sense of the Kullback-Leibler divergence. To the best of our knowledge, this is the first work on providing theoretical guarantees for implicit variational inference." @default.
- W3159719175 created "2021-05-10" @default.
- W3159719175 creator A5002768909 @default.
- W3159719175 creator A5033365412 @default.
- W3159719175 creator A5034514833 @default.
- W3159719175 creator A5075421264 @default.
- W3159719175 creator A5080216523 @default.
- W3159719175 date "2021-03-18" @default.
- W3159719175 modified "2023-09-27" @default.
- W3159719175 title "Statistical Guarantees for Transformation Based Models with applications to Implicit Variational Inference" @default.
- W3159719175 hasPublicationYear "2021" @default.
- W3159719175 type Work @default.
- W3159719175 sameAs 3159719175 @default.
- W3159719175 citedByCount "0" @default.
- W3159719175 crossrefType "proceedings-article" @default.
- W3159719175 hasAuthorship W3159719175A5002768909 @default.
- W3159719175 hasAuthorship W3159719175A5033365412 @default.
- W3159719175 hasAuthorship W3159719175A5034514833 @default.
- W3159719175 hasAuthorship W3159719175A5075421264 @default.
- W3159719175 hasAuthorship W3159719175A5080216523 @default.
- W3159719175 hasConcept C104317684 @default.
- W3159719175 hasConcept C105795698 @default.
- W3159719175 hasConcept C11413529 @default.
- W3159719175 hasConcept C117251300 @default.
- W3159719175 hasConcept C126255220 @default.
- W3159719175 hasConcept C154945302 @default.
- W3159719175 hasConcept C185429906 @default.
- W3159719175 hasConcept C185592680 @default.
- W3159719175 hasConcept C189508267 @default.
- W3159719175 hasConcept C204241405 @default.
- W3159719175 hasConcept C2776214188 @default.
- W3159719175 hasConcept C28826006 @default.
- W3159719175 hasConcept C33923547 @default.
- W3159719175 hasConcept C41008148 @default.
- W3159719175 hasConcept C51167844 @default.
- W3159719175 hasConcept C55493867 @default.
- W3159719175 hasConceptScore W3159719175C104317684 @default.
- W3159719175 hasConceptScore W3159719175C105795698 @default.
- W3159719175 hasConceptScore W3159719175C11413529 @default.
- W3159719175 hasConceptScore W3159719175C117251300 @default.
- W3159719175 hasConceptScore W3159719175C126255220 @default.
- W3159719175 hasConceptScore W3159719175C154945302 @default.
- W3159719175 hasConceptScore W3159719175C185429906 @default.
- W3159719175 hasConceptScore W3159719175C185592680 @default.
- W3159719175 hasConceptScore W3159719175C189508267 @default.
- W3159719175 hasConceptScore W3159719175C204241405 @default.
- W3159719175 hasConceptScore W3159719175C2776214188 @default.
- W3159719175 hasConceptScore W3159719175C28826006 @default.
- W3159719175 hasConceptScore W3159719175C33923547 @default.
- W3159719175 hasConceptScore W3159719175C41008148 @default.
- W3159719175 hasConceptScore W3159719175C51167844 @default.
- W3159719175 hasConceptScore W3159719175C55493867 @default.
- W3159719175 hasLocation W31597191751 @default.
- W3159719175 hasOpenAccess W3159719175 @default.
- W3159719175 hasPrimaryLocation W31597191751 @default.
- W3159719175 hasRelatedWork W2121693152 @default.
- W3159719175 hasRelatedWork W2148111240 @default.
- W3159719175 hasRelatedWork W2167923228 @default.
- W3159719175 hasRelatedWork W2271522117 @default.
- W3159719175 hasRelatedWork W2728803307 @default.
- W3159719175 hasRelatedWork W2753260804 @default.
- W3159719175 hasRelatedWork W2765737382 @default.
- W3159719175 hasRelatedWork W2767137871 @default.
- W3159719175 hasRelatedWork W2768447495 @default.
- W3159719175 hasRelatedWork W2784067649 @default.
- W3159719175 hasRelatedWork W2847062694 @default.
- W3159719175 hasRelatedWork W2886436016 @default.
- W3159719175 hasRelatedWork W2889762000 @default.
- W3159719175 hasRelatedWork W2943968367 @default.
- W3159719175 hasRelatedWork W2963090522 @default.
- W3159719175 hasRelatedWork W2965728583 @default.
- W3159719175 hasRelatedWork W3097459875 @default.
- W3159719175 hasRelatedWork W3111366808 @default.
- W3159719175 hasRelatedWork W3133733630 @default.
- W3159719175 hasRelatedWork W3197968517 @default.
- W3159719175 isParatext "false" @default.
- W3159719175 isRetracted "false" @default.
- W3159719175 magId "3159719175" @default.
- W3159719175 workType "article" @default.