Automatic Differentiation for Complex Valued SVD

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.

arXiv comment4.2 pages

Cited by in corpus (4)

• Automatic Differentiable Monte Carlo: Theory and Application
• Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications
• Use and implementation of autodifferentiation in tensor network methods with complex scalars
• Differentiate Everything with a Reversible Embeded Domain-Specific Language