English

Backpropagation through Back Substitution with a Backslash

Numerical Analysis 2023-09-01 v2 Machine Learning Numerical Analysis

Abstract

We present a linear algebra formulation of backpropagation which allows the calculation of gradients by using a generically written ``backslash'' or Gaussian elimination on triangular systems of equations. Generally, the matrix elements are operators. This paper has three contributions: (i) it is of intellectual value to replace traditional treatments of automatic differentiation with a (left acting) operator theoretic, graph-based approach; (ii) operators can be readily placed in matrices in software in programming languages such as Julia as an implementation option; (iii) we introduce a novel notation, ``transpose dot'' operator ``{}T\{\}^{T_\bullet}'' that allows for the reversal of operators. We further demonstrate the elegance of the operators approach in a suitable programming language consisting of generic linear algebra operators such as Julia \cite{bezanson2017julia}, and that it is possible to realize this abstraction in code. Our implementation shows how generic linear algebra can allow operators as elements of matrices. In contrast to ``operator overloading,'' where backslash would normally have to be rewritten to take advantage of operators, with ``generic programming'' there is no such need.

Cite

@article{arxiv.2303.15449,
  title  = {Backpropagation through Back Substitution with a Backslash},
  author = {Alan Edelman and Ekin Akyurek and Yuyang Wang},
  journal= {arXiv preprint arXiv:2303.15449},
  year   = {2023}
}

Comments

22 pages

R2 v1 2026-06-28T09:36:22.760Z