Metraipolis › archive › dc_43826034bd65
Theoretical Analysis of Thermodynamic Matrix Inversion: First-order Equivalence to Preconditioned Gradient Descent and Implications for Analog Computing — arXiv:2608.09743
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09743
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:08:08.063Z
- SHA-256 of the archived text
0d1d2497087b8b5af36c77d64ec23c619ef882f130fb46ba005bb0244feba725- Stable URL of this page
https://metraipolis.com/documento/dc_43826034bd65
How to cite
Theoretical Analysis of Thermodynamic Matrix Inversion: First-order Equivalence to Preconditioned Gradient Descent and Implications for Analog Computing — arXiv:2608.09743 — arXiv (en), https://arxiv.org/abs/2608.09743 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43826034bd65 (Metraipolis archive dc_43826034bd65, sha256 0d1d2497087b8b5af36c77d64ec23c619ef882f130fb46ba005bb0244feba725)
BibTeX
@misc{dc43826034bd65,
title = {Theoretical Analysis of Thermodynamic Matrix Inversion: First-order Equivalence to Preconditioned Gradient Descent and Implications for Analog Computing — arXiv:2608.09743},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09743},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43826034bd65; sha256 0d1d2497087b8b5af36c77d64ec23c619ef882f130fb46ba005bb0244feba725},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09743. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent research has demonstrated the possibility of exploiting the thermodynamics of coupled electrical oscillators to implement computational tasks such as matrix inversion. While physical implementations rely on thermal noise to drive equilibration, we show that the underlying dynamics reduce to a deterministic iterative algorithm. Building on the framework of Aifer et al., we analyze the moment evolution of the Ornstein-Uhlenbeck process governing thermodynamic symmetric positive definite (SPD) matrix inversion. We prove that to a first-order approximation, the covariance dynamics are mathematically identical to preconditioned gradient descent on the Frobenius norm of the residual $\tilde{A}^{-1}A-I$. This equivalence demonstrates that thermal fluctuations, while essential for physical thermodynamic hardware, are algorithmically redundant for convex problems with a single global minimum. We validate the resulting algorithm against Thermox (Duffield et al.), a stochastic thermodynamic simulator, achieving speedups exceeding 100,000-fold while remaining competitive with the Newton-Schulz iteration. We also demonstrate acceleration through Schur complement techniques. These results establish a rigorous link between analog thermodynamic computing, statistical physics, and deterministic optimization methods.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-11 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.09743 — 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 2026-10-19T09:05:02.987Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).