Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320561208> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4320561208 abstract "Gradients of probabilistic model likelihoods with respect to their parameters are essential for modern computational statistics and machine learning. These calculations are readily available for arbitrary models via automatic differentiation implemented in general-purpose machine-learning libraries such as TensorFlow and PyTorch. Although these libraries are highly optimized, it is not clear if their general-purpose nature will limit their algorithmic complexity or implementation speed for the phylogenetic case compared to phylogenetics-specific code. In this paper, we compare six gradient implementations of the phylogenetic likelihood functions, in isolation and also as part of a variational inference procedure. We find that although automatic differentiation can scale approximately linearly in tree size, it is much slower than the carefully-implemented gradient calculation for tree likelihood and ratio transformation operations. We conclude that a mixed approach combining phylogenetic libraries with machine learning libraries will provide the optimal combination of speed and model flexibility moving forward." @default.
- W4320561208 created "2023-02-15" @default.
- W4320561208 creator A5039905606 @default.
- W4320561208 creator A5047020208 @default.
- W4320561208 creator A5053321930 @default.
- W4320561208 creator A5058091732 @default.
- W4320561208 creator A5070262421 @default.
- W4320561208 creator A5071445210 @default.
- W4320561208 creator A5072834063 @default.
- W4320561208 date "2022-11-03" @default.
- W4320561208 modified "2023-09-30" @default.
- W4320561208 title "Automatic differentiation is no panacea for phylogenetic gradient computation" @default.
- W4320561208 doi "https://doi.org/10.48550/arxiv.2211.02168" @default.
- W4320561208 hasPublicationYear "2022" @default.
- W4320561208 type Work @default.
- W4320561208 citedByCount "0" @default.
- W4320561208 crossrefType "posted-content" @default.
- W4320561208 hasAuthorship W4320561208A5039905606 @default.
- W4320561208 hasAuthorship W4320561208A5047020208 @default.
- W4320561208 hasAuthorship W4320561208A5053321930 @default.
- W4320561208 hasAuthorship W4320561208A5058091732 @default.
- W4320561208 hasAuthorship W4320561208A5070262421 @default.
- W4320561208 hasAuthorship W4320561208A5071445210 @default.
- W4320561208 hasAuthorship W4320561208A5072834063 @default.
- W4320561208 hasConcept C104317684 @default.
- W4320561208 hasConcept C105795698 @default.
- W4320561208 hasConcept C113174947 @default.
- W4320561208 hasConcept C11413529 @default.
- W4320561208 hasConcept C119857082 @default.
- W4320561208 hasConcept C133512626 @default.
- W4320561208 hasConcept C134306372 @default.
- W4320561208 hasConcept C154945302 @default.
- W4320561208 hasConcept C185592680 @default.
- W4320561208 hasConcept C193252679 @default.
- W4320561208 hasConcept C204241405 @default.
- W4320561208 hasConcept C2776214188 @default.
- W4320561208 hasConcept C2780598303 @default.
- W4320561208 hasConcept C33923547 @default.
- W4320561208 hasConcept C41008148 @default.
- W4320561208 hasConcept C45374587 @default.
- W4320561208 hasConcept C49937458 @default.
- W4320561208 hasConcept C55493867 @default.
- W4320561208 hasConcept C80444323 @default.
- W4320561208 hasConceptScore W4320561208C104317684 @default.
- W4320561208 hasConceptScore W4320561208C105795698 @default.
- W4320561208 hasConceptScore W4320561208C113174947 @default.
- W4320561208 hasConceptScore W4320561208C11413529 @default.
- W4320561208 hasConceptScore W4320561208C119857082 @default.
- W4320561208 hasConceptScore W4320561208C133512626 @default.
- W4320561208 hasConceptScore W4320561208C134306372 @default.
- W4320561208 hasConceptScore W4320561208C154945302 @default.
- W4320561208 hasConceptScore W4320561208C185592680 @default.
- W4320561208 hasConceptScore W4320561208C193252679 @default.
- W4320561208 hasConceptScore W4320561208C204241405 @default.
- W4320561208 hasConceptScore W4320561208C2776214188 @default.
- W4320561208 hasConceptScore W4320561208C2780598303 @default.
- W4320561208 hasConceptScore W4320561208C33923547 @default.
- W4320561208 hasConceptScore W4320561208C41008148 @default.
- W4320561208 hasConceptScore W4320561208C45374587 @default.
- W4320561208 hasConceptScore W4320561208C49937458 @default.
- W4320561208 hasConceptScore W4320561208C55493867 @default.
- W4320561208 hasConceptScore W4320561208C80444323 @default.
- W4320561208 hasLocation W43205612081 @default.
- W4320561208 hasOpenAccess W4320561208 @default.
- W4320561208 hasPrimaryLocation W43205612081 @default.
- W4320561208 hasRelatedWork W152877024 @default.
- W4320561208 hasRelatedWork W1679582220 @default.
- W4320561208 hasRelatedWork W2269333382 @default.
- W4320561208 hasRelatedWork W2511279186 @default.
- W4320561208 hasRelatedWork W2766697009 @default.
- W4320561208 hasRelatedWork W2886383139 @default.
- W4320561208 hasRelatedWork W2926374695 @default.
- W4320561208 hasRelatedWork W2991219963 @default.
- W4320561208 hasRelatedWork W3005235420 @default.
- W4320561208 hasRelatedWork W3209482076 @default.
- W4320561208 isParatext "false" @default.
- W4320561208 isRetracted "false" @default.
- W4320561208 workType "article" @default.