Learned Diffractive Optics for Quantum-Optimal Inference
Abstract
Quantum mechanics sets the ultimate bounds on photon-limited sensing, yet practical measurements attaining these bounds are known only in special cases. This is particularly the case for visual sensing problems, where the goal is to infer features of a distant object based on the spatial structure of the light field it emits or reflects. Because of the potentially complex structure of such objects and fields, constructing optimal measurements on them is a challenging task. Here, we apply learned diffractive optics to state discrimination and parameter estimation of coherent and diffraction-limited incoherent light fields under a restricted photon budget. Optimized directly on each task's figure of merit, without prior knowledge of the optimal measurement, the physically realizable diffractive optical neural networks substantially outperform standard measurements and approach the quantum limits for a given number of photons as well as in the asymptotic limit.
Related
- Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing
- Quantum-Correlation-Based Multi-Emitter Localization in Information-Limited Regimes via Learned Inference
- Optimal Diffractive Focusing of Vortex Beams
- Quantum computing and quantum optics with recoiled free electrons
- Quantum simulation of wave optics in weakly inhomogeneous media using block encoding
BibTeX
@misc{filipovich2026learned,
title = {{Learned Diffractive Optics for Quantum-Optimal Inference}},
author = {Matthew J. Filipovich and Alexander Duplinskii and A. I. Lvovsky},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.08014},
eprint = {2609.08014},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.08014},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learned Diffractive Optics for Quantum-Optimal Inference
AU - Matthew J. Filipovich
AU - Alexander Duplinskii
AU - A. I. Lvovsky
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2609.08014
UR - https://arxiv.org/abs/2609.08014
AB - Quantum mechanics sets the ultimate bounds on photon-limited sensing, yet practical measurements attaining these bounds are known only in special cases. This is particularly the case for visual sensing problems, where the goal is to infer features of a distant object based on the spatial structure of the light field it emits or reflects. Because of the potentially complex structure of such objects and fields, constructing optimal measurements on them is a challenging task. Here, we apply learned diffractive optics to state discrimination and parameter estimation of coherent and diffraction-limited incoherent light fields under a restricted photon budget. Optimized directly on each task's figure of merit, without prior knowledge of the optimal measurement, the physically realizable diffractive optical neural networks substantially outperform standard measurements and approach the quantum limits for a given number of photons as well as in the asymptotic limit.
ER -