ML Anthology

MatrixCalculus.org - Computing Derivatives of Matrix and Tensor Expressions

Sören Laue, Matthias Mitterreiter, Joachim Giesen
ECML-PKDD 2019 pp. 769-772
doi:10.1007/978-3-030-46133-1_48 /ecmlpkdd/2019/laue2019ecmlpkdd-matrixcalculus/

Abstract

Computing derivatives of matrix and tensor expressions is an integral part of developing and implementing optimization algorithms in machine learning. However, it is a time-consuming and error-prone task when done by hand. Here, we present the first system that performs matrix and tensor calculus automatically.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Laue et al. "MatrixCalculus.org - Computing Derivatives of Matrix and Tensor Expressions." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019. doi:10.1007/978-3-030-46133-1_48

Markdown

[Laue et al. "MatrixCalculus.org - Computing Derivatives of Matrix and Tensor Expressions." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019.](https://mlanthology.org/ecmlpkdd/2019/laue2019ecmlpkdd-matrixcalculus/) doi:10.1007/978-3-030-46133-1_48

BibTeX

@inproceedings{laue2019ecmlpkdd-matrixcalculus,
  title     = {{MatrixCalculus.org - Computing Derivatives of Matrix and Tensor Expressions}},
  author    = {Laue, Sören and Mitterreiter, Matthias and Giesen, Joachim},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2019},
  pages     = {769-772},
  doi       = {10.1007/978-3-030-46133-1_48},
  url       = {https://mlanthology.org/ecmlpkdd/2019/laue2019ecmlpkdd-matrixcalculus/}
}