当前位置:
X-MOL 学术
›
arXiv.cs.MS
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
QR and LQ Decomposition Matrix Backpropagation Algorithms for Square, Wide, and Deep Matrices and Their Software Implementation
arXiv - CS - Mathematical Software Pub Date : 2020-09-19 , DOI: arxiv-2009.10071 Denisa A.O. Roberts and Lucas R. Roberts
arXiv - CS - Mathematical Software Pub Date : 2020-09-19 , DOI: arxiv-2009.10071 Denisa A.O. Roberts and Lucas R. Roberts
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. 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, and hopefully, leads to new lines of research.
中文翻译:
方、宽、深矩阵的 QR 和 LQ 分解矩阵反向传播算法及其软件实现
本文介绍了矩阵 $A_{m, n}$ 的 QR 分解的矩阵反向传播算法,这些矩阵是正方形 (m = n)、宽 (m < n) 或深 (m > n),秩为 $k = min(m, n)$。此外,我们为枢轴(满秩)QR 分解和深度输入矩阵的 LQ 分解推导出新的矩阵反向传播结果。可微 QR 分解提供了一种数值稳定、计算效率高的方法来解决机器学习和计算机视觉中经常遇到的最小二乘问题。跨流行的深度学习框架(PyTorch、TensorFlow、MXNet)的软件实现结合了深度学习社区中通用的方法。此外,
更新日期:2020-11-17
中文翻译:
方、宽、深矩阵的 QR 和 LQ 分解矩阵反向传播算法及其软件实现
本文介绍了矩阵 $A_{m, n}$ 的 QR 分解的矩阵反向传播算法,这些矩阵是正方形 (m = n)、宽 (m < n) 或深 (m > n),秩为 $k = min(m, n)$。此外,我们为枢轴(满秩)QR 分解和深度输入矩阵的 LQ 分解推导出新的矩阵反向传播结果。可微 QR 分解提供了一种数值稳定、计算效率高的方法来解决机器学习和计算机视觉中经常遇到的最小二乘问题。跨流行的深度学习框架(PyTorch、TensorFlow、MXNet)的软件实现结合了深度学习社区中通用的方法。此外,