Low-depth, compact and error-tolerant photonic matrix-vector multiplication beyond the unitary group

2024/08/01 by Suren A. Fldzhyan, Fldzhyan, S. A., M. Yu. Saygin +3 · 2 citations
Computer Science · Engineering · #Advanced Photonic Communication Systems #FOS: Physical sciences #Neural Networks and Reservoir Computing #Optical Network Technologies #Optics (physics.optics) #Quantum Physics (quant-ph)

paper · pdf · doi:10.48550/arxiv.2408.00669

openalex publication_date 2024/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large-scale programmable photonic circuits are opening up new possibilities for information processing providing fast and energy-efficient means for matrix-vector multiplication. Here, we introduce a novel architecture of photonic circuits capable of implementing non-unitary transfer matrices, usually required by photonic neural networks, iterative equation solvers or quantum samplers. Our architecture exploits compact low-depth beam-splitter meshes rather than bulky fully connected mixing blocks used in previous designs, making it more compatible with planar integrated photonics technology. We have shown that photonic circuits designed with our architecture have lower depth than their standard counterparts and are extremely tolerant to hardware errors.

Cited by

• Complexity-energy trade-off in programmable unitary interferometers
• Leveraging machine learning features for linear optical interferometer control

Related

• Universal low-depth two-unitary design of programmable photonic circuits
• Embedding Matrices in Programmable Photonic Networks with Flexible Depth and Width
• Waveguide-multiplexed photonic matrix-vector multiplication processor using multiport photodetectors
• Programmable photonic waveguide arrays: opportunities and challenges
• SUANPAN: Scalable Photonic Linear Vector Machine