EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic Differentiation is no Panacea for Phylogenetic Gradient Computation

Mathieu Fourment iD, Christiaan J Swanepoel, Jared G Galloway, Xiang Ji, Karthik Gangavarapu, Marc A Suchard iD, Frederick A Matsen Iv iD

Genome Biology and Evolution · 01.06.2023 · 15 (6)

DOI: 10.1093/gbe/evad099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genome Biology and Evolution, online erschienen am 02.06.2023. Verfasst von Mathieu Fourment und 6 weiteren Autor:innen. Beteiligte Einrichtung: Australian Institute for Microbiology and Infection, University of Technology Sydney, Ultimo, NSW, Australia. Hauptthemen laut MEDLINE: Models, Statistical, Machine Learning. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, Howard Hughes Medical Institute, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, StatisticalMachine LearningPhylogenyLikelihood FunctionsAlgorithms

Stichwörter der Autor:innen

Bayesian inferencegradientphylogeneticsvariational inference

Autor:innen und Institutionen

  • Australian Institute for Microbiology and Infection, University of Technology Sydney, Ultimo, NSW, Australia.
  • Centre for Computational Evolution, The University of Auckland, Auckland, New Zealand.
  • School of Computer Science, The University of Auckland, Auckland, New Zealand.
  • Public Health Sciences Division, Fred Hutchinson Cancer Research Center, Seattle, Washington, USA.
  • Department of Mathematics, Tulane University, New Orleans, Louisiana, USA.
  • Department of Human Genetics, University of California, Los Angeles, California, USA.

ORCID-Profile: Mathieu Fourment, Marc A Suchard, Frederick A Matsen Iv

Förderung

  • NIAID NIH HHS
  • Howard Hughes Medical Institute
  • NIH HHS

Zitieren

APA

Fourment, M., Swanepoel, C. J., Galloway, J. G., Ji, X., Gangavarapu, K., Suchard, M. A., & Matsen Iv, F. A. (2023). Automatic Differentiation is no Panacea for Phylogenetic Gradient Computation. Genome Biology and Evolution, 15(6). https://doi.org/10.1093/gbe/evad099

Vancouver

Fourment M, Swanepoel CJ, Galloway JG, Ji X, Gangavarapu K, Suchard MA, et al. Automatic Differentiation is no Panacea for Phylogenetic Gradient Computation. Genome Biology and Evolution. 2023;15(6). doi:10.1093/gbe/evad099

BibTeX
@article{Fourment2023,
  author = {Fourment, Mathieu and Swanepoel, Christiaan J and Galloway, Jared G and Ji, Xiang and Gangavarapu, Karthik and Suchard, Marc A and Matsen Iv, Frederick A},
  title = {Automatic Differentiation is no Panacea for Phylogenetic Gradient Computation},
  journal = {Genome Biology and Evolution},
  year = {2023},
  volume = {15},
  number = {6},
  doi = {10.1093/gbe/evad099}
}
Kostenlos starten →