Matches in SemOpenAlex for { <https://semopenalex.org/work/W2751066228> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2751066228 abstract "Recently, there has been a growing interest in the problem of learning rich implicit models - those from which we can sample, but can not evaluate their density. These models apply some parametric function, such as a deep network, to a base measure, and are learned end-to-end using stochastic optimization. One strategy of devising a loss function is through the statistics of two sample tests - if we can fool a statistical test, the learned distribution should be a good model of the true data. However, not all tests can easily fit into this framework, as they might not be differentiable with respect to the data points, and hence with respect to the parameters of the implicit model. Motivated by this problem, in this paper we show how two such classical tests, the Friedman-Rafsky and k-nearest neighbour tests, can be effectively smoothed using ideas from undirected graphical models - the matrix tree theorem and cardinality potentials. Moreover, as we show experimentally, smoothing can significantly increase the power of the test, which might of of independent interest. Finally, we apply our method to learn implicit models." @default.
- W2751066228 created "2017-09-15" @default.
- W2751066228 creator A5010814788 @default.
- W2751066228 creator A5070631081 @default.
- W2751066228 date "2017-09-04" @default.
- W2751066228 modified "2023-09-27" @default.
- W2751066228 title "Learning Implicit Generative Models Using Differentiable Graph Tests." @default.
- W2751066228 cites W1571024744 @default.
- W2751066228 cites W2003201102 @default.
- W2751066228 cites W2027390033 @default.
- W2751066228 cites W2039479672 @default.
- W2751066228 cites W2045650933 @default.
- W2751066228 cites W2068276287 @default.
- W2751066228 cites W2077584453 @default.
- W2751066228 cites W2101234009 @default.
- W2751066228 cites W2103679238 @default.
- W2751066228 cites W2111527197 @default.
- W2751066228 cites W2112796928 @default.
- W2751066228 cites W2120340025 @default.
- W2751066228 cites W2144935315 @default.
- W2751066228 cites W2161627023 @default.
- W2751066228 cites W2212660284 @default.
- W2751066228 cites W2221345128 @default.
- W2751066228 cites W2949995983 @default.
- W2751066228 cites W2950292946 @default.
- W2751066228 cites W2950863313 @default.
- W2751066228 cites W2962867415 @default.
- W2751066228 cites W2964121744 @default.
- W2751066228 hasPublicationYear "2017" @default.
- W2751066228 type Work @default.
- W2751066228 sameAs 2751066228 @default.
- W2751066228 citedByCount "3" @default.
- W2751066228 countsByYear W27510662282018 @default.
- W2751066228 countsByYear W27510662282020 @default.
- W2751066228 countsByYear W27510662282021 @default.
- W2751066228 crossrefType "posted-content" @default.
- W2751066228 hasAuthorship W2751066228A5010814788 @default.
- W2751066228 hasAuthorship W2751066228A5070631081 @default.
- W2751066228 hasConcept C105795698 @default.
- W2751066228 hasConcept C11413529 @default.
- W2751066228 hasConcept C132525143 @default.
- W2751066228 hasConcept C134306372 @default.
- W2751066228 hasConcept C154945302 @default.
- W2751066228 hasConcept C167966045 @default.
- W2751066228 hasConcept C202615002 @default.
- W2751066228 hasConcept C28826006 @default.
- W2751066228 hasConcept C33923547 @default.
- W2751066228 hasConcept C3770464 @default.
- W2751066228 hasConcept C39890363 @default.
- W2751066228 hasConcept C41008148 @default.
- W2751066228 hasConcept C80444323 @default.
- W2751066228 hasConcept C87007009 @default.
- W2751066228 hasConceptScore W2751066228C105795698 @default.
- W2751066228 hasConceptScore W2751066228C11413529 @default.
- W2751066228 hasConceptScore W2751066228C132525143 @default.
- W2751066228 hasConceptScore W2751066228C134306372 @default.
- W2751066228 hasConceptScore W2751066228C154945302 @default.
- W2751066228 hasConceptScore W2751066228C167966045 @default.
- W2751066228 hasConceptScore W2751066228C202615002 @default.
- W2751066228 hasConceptScore W2751066228C28826006 @default.
- W2751066228 hasConceptScore W2751066228C33923547 @default.
- W2751066228 hasConceptScore W2751066228C3770464 @default.
- W2751066228 hasConceptScore W2751066228C39890363 @default.
- W2751066228 hasConceptScore W2751066228C41008148 @default.
- W2751066228 hasConceptScore W2751066228C80444323 @default.
- W2751066228 hasConceptScore W2751066228C87007009 @default.
- W2751066228 hasLocation W27510662281 @default.
- W2751066228 hasOpenAccess W2751066228 @default.
- W2751066228 hasPrimaryLocation W27510662281 @default.
- W2751066228 hasRelatedWork W15601695 @default.
- W2751066228 hasRelatedWork W1560621288 @default.
- W2751066228 hasRelatedWork W1755468095 @default.
- W2751066228 hasRelatedWork W1913920913 @default.
- W2751066228 hasRelatedWork W1914062059 @default.
- W2751066228 hasRelatedWork W2004036579 @default.
- W2751066228 hasRelatedWork W2018808934 @default.
- W2751066228 hasRelatedWork W2023174171 @default.
- W2751066228 hasRelatedWork W2125497405 @default.
- W2751066228 hasRelatedWork W2130186484 @default.
- W2751066228 hasRelatedWork W2156005874 @default.
- W2751066228 hasRelatedWork W2198300770 @default.
- W2751066228 hasRelatedWork W2554736449 @default.
- W2751066228 hasRelatedWork W2963325933 @default.
- W2751066228 hasRelatedWork W3005529192 @default.
- W2751066228 hasRelatedWork W3035870802 @default.
- W2751066228 hasRelatedWork W3035909655 @default.
- W2751066228 hasRelatedWork W3101300262 @default.
- W2751066228 hasRelatedWork W3133989806 @default.
- W2751066228 hasRelatedWork W811226091 @default.
- W2751066228 isParatext "false" @default.
- W2751066228 isRetracted "false" @default.
- W2751066228 magId "2751066228" @default.
- W2751066228 workType "article" @default.