Metraipolis › archive › dc_9685f288fe4f
Unifying Physical Backpropagation — arXiv:2608.11585
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11585
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:40:15.966Z
- SHA-256 of the archived text
8f1fe63cb680ea6e72c808a9c0999213984fa4a07be15f4ba7a2b82cd29315b1- Stable URL of this page
https://metraipolis.com/documento/dc_9685f288fe4f
How to cite
Unifying Physical Backpropagation — arXiv:2608.11585 — arXiv (en), https://arxiv.org/abs/2608.11585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9685f288fe4f (Metraipolis archive dc_9685f288fe4f, sha256 8f1fe63cb680ea6e72c808a9c0999213984fa4a07be15f4ba7a2b82cd29315b1)
BibTeX
@misc{dc9685f288fe4f,
title = {Unifying Physical Backpropagation — arXiv:2608.11585},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11585},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9685f288fe4f; sha256 8f1fe63cb680ea6e72c808a9c0999213984fa4a07be15f4ba7a2b82cd29315b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a digital twin suffers from a model-reality gap. On-device gradient computation could resolve this issue, and a handful of theoretical and experimental studies have proposed ways to achieve it. Yet a unifying theory identifying when a physical system can compute the gradient of its own performance has been missing. Here we develop such a unification based on the adjoint method: we identify sufficient conditions under which the adjoint field required for formally exact gradients can be generated on the same hardware that performs the computation. Linear and nonlinear systems obey fundamentally different conditions: for linear systems, damping or gain is admissible provided reciprocity is preserved. For nonlinear trajectory systems, the sufficient conditions are reciprocity of the linearized system and the existence of a time-reversal mirror. Algorithmically, the nonlinear case requires infinitesimal nudging, whereas linear systems admit a finite-amplitude experiment. We recover (quantum) Equilibrium Propagation, Hamiltonian echo backpropagation, fully forward mode training and in situ gradient methods in integrated-photonic and free-space-optical systems. Finally, we show that reciprocity is a special case of more general intertwining conditions. For linear systems, these permit exact on-device gradients in a class of non-Hermitian, non-reciprocal systems. For nonlinear trajectories, they combine with generalized time-reversal mirrors to cover, e.g., PT-symmetric equations. The framework also includes time-dependent parameters and Onsager-reciprocal dynamics, providing a unified basis for formally exact physical learning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG). Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Emerging Technologies (cs.ET); Machine Learning (cs.LG); Optics (physics.optics). Pagina del lavoro: https://arxiv.org/abs/2608.11585 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T05:18:32.538Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).