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.
- Publication:
-
arXiv e-prints
- Pub Date:
- September 2019
- DOI:
- arXiv:
- arXiv:1909.02659
- Bibcode:
- 2019arXiv190902659W
- Keywords:
-
- Mathematics - Numerical Analysis;
- Condensed Matter - Statistical Mechanics;
- Condensed Matter - Strongly Correlated Electrons;
- Computer Science - Machine Learning;
- Quantum Physics;
- Statistics - Machine Learning
- E-Print:
- 4.2 pages