Physical Adjoint Learning in Wave Systems with Asymmetric Couplings
Abstract
Developing self-optimizing physical systems that learn directly from their response to external stimuli offers a promising route toward adaptive and intelligent machines. A key ingredient is the ability to evaluate optimization gradients within the physical hardware, bypassing the need for accurate numerical models. In wave systems, \textit{in-situ} adjoint methods provide this capability by exploiting reciprocity to physically realize the adjoint dynamics. However, this approach generally breaks down in nonreciprocal systems, where the adjoint field cannot be directly accessed through the original device. Here, we develop an \textit{in-situ} adjoint optimization framework that extends physical gradient computation to wave systems with asymmetric couplings through computationally low-cost similarity transformations between the forward and transposed operators. We utilize available degrees of freedom like tailored injected excitations, targeted measurements, and tunable parameters, to enable adjoint field reconstruction through forward experiments on the same physical platform. We demonstrate the versatility of the protocol through broadband transmission and isolation, coherent perfect absorption, programmable wavefront shaping, and spatially selective sensing. Our results provide a route to self-optimization in complex nonreciprocal wave systems through efficient physical gradient-based learning. The number of experiments required by the protocol does not increase with the number of optimization parameters, and the method remains applicable even when parts of the system are completely inaccessible.
Related
- Physical policy gradient theorem for in situ stochastic-adjoint training
- Symmetry-driven in-situ physical adjoint computing beyond reciprocity
- Asymmetric Coupling Anisotropy for Causal Information Filtering in Physical Reservoirs
- A systematic study of hydrodynamic attractors in periodically driven systems at weak and strong couplings
- Extracting dipole orientations from asymmetric plasmonic nanostructures towards machine-learning-assisted spectropolarimetry
BibTeX
@misc{fernandezalcazar2026physical,
title = {{Physical Adjoint Learning in Wave Systems with Asymmetric Couplings}},
author = {Lucas J. Fernández-Alcázar and John Guillamon and Krishna Joshi and Tsampikos Kottos},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.34815},
eprint = {2610.34815},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.34815},
}
RIS
TY - UNPB
TI - Physical Adjoint Learning in Wave Systems with Asymmetric Couplings
AU - Lucas J. Fernández-Alcázar
AU - John Guillamon
AU - Krishna Joshi
AU - Tsampikos Kottos
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.34815
UR - https://arxiv.org/abs/2610.34815
AB - Developing self-optimizing physical systems that learn directly from their response to external stimuli offers a promising route toward adaptive and intelligent machines. A key ingredient is the ability to evaluate optimization gradients within the physical hardware, bypassing the need for accurate numerical models. In wave systems, \textit{in-situ} adjoint methods provide this capability by exploiting reciprocity to physically realize the adjoint dynamics. However, this approach generally breaks down in nonreciprocal systems, where the adjoint field cannot be directly accessed through the original device. Here, we develop an \textit{in-situ} adjoint optimization framework that extends physical gradient computation to wave systems with asymmetric couplings through computationally low-cost similarity transformations between the forward and transposed operators. We utilize available degrees of freedom like tailored injected excitations, targeted measurements, and tunable parameters, to enable adjoint field reconstruction through forward experiments on the same physical platform. We demonstrate the versatility of the protocol through broadband transmission and isolation, coherent perfect absorption, programmable wavefront shaping, and spatially selective sensing. Our results provide a route to self-optimization in complex nonreciprocal wave systems through efficient physical gradient-based learning. The number of experiments required by the protocol does not increase with the number of optimization parameters, and the method remains applicable even when parts of the system are completely inaccessible.
ER -