QR and LQ Decomposition Matrix Backpropagation Algorithms for Square, Wide, and Deep -- Real or Complex -- Matrices and Their Software Implementation

Abstract

This article presents matrix backpropagation algorithms for the QR decomposition of matrices $A_{m,n}$, that are either square (m = n), wide (m < n), or deep (m > n), with rank $k=min(m,n)$. Furthermore, we derive novel matrix backpropagation results for the pivoted (full-rank) QR decomposition and for the LQ decomposition of deep input matrices. Differentiable QR decomposition offers a numerically stable, computationally efficient method to solve least squares problems frequently encountered in machine learning and computer vision. Other use cases such as graph learning and network compression are listed in the article. Software implementation across popular deep learning frameworks (PyTorch, TensorFlow, MXNet) incorporate the methods for general use within the deep learning community. Furthermore, this article aids the practitioner in understanding the matrix backpropagation methodology as part of larger computational graphs.

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Differentiable Programming Tensor Networks
• Training Deep Networks with Structured Layers by Matrix Backpropagation
• Use and implementation of autodifferentiation in tensor network methods with complex scalars
• Algorithmic Differentiation of Linear Algebra Functions with Application in Optimum Experimental Design (Extended Version)