Back to Search Start Over

Automatic Differentiation for Complex Valued SVD

Authors :
Wan, Zhou-Quan
Zhang, Shi-Xin
Publication Year :
2019

Abstract

In this note, we report the back propagation formula for complex valued singular value decompositions (SVD). This formula is an important ingredient for a complete automatic differentiation(AD) infrastructure in terms of complex numbers, and it is also the key to understand and utilize AD in tensor networks.<br />Comment: 4.2 pages

Subjects

Subjects :
Mathematics - Numerical Analysis
Condensed Matter - Statistical Mechanics
Condensed Matter - Strongly Correlated Electrons
Computer Science - Machine Learning
Quantum Physics
Statistics - Machine Learning

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1909.02659
Document Type :
Working Paper

Tools

Authors Abstract Subjects Details