arXiv:1909.02659
Automatic Differentiation for Complex Valued SVD
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A tensor network approach for chaotic time series prediction
Quantum Methods for Managing Ambiguity in Natural Language Processing
tn4ml: Tensor Network Training and Customization for Machine Learning
Comb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces
LTNtorch: PyTorch Implementation of Logic Tensor Networks
Learning out-of-time-ordered correlators with classical kernel methods
토론
이 논문과 연결된 포럼 글이 아직 없습니다.