Metraipolis › archive › dc_fe4e687d2a4f

Fast simulation of nonlinear deep resistive networks for energy-based computation — arXiv:2609.07356

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07356
License (as archived)
CC0-1.0
Archived
2026-10-16T15:40:34.319Z
SHA-256 of the archived text
c8c8f60995abc1ff488bebdf520cfc937bcbc3ac40492628f04fe9f1e34a13e5
Stable URL of this page
https://metraipolis.com/documento/dc_fe4e687d2a4f

How to cite

Fast simulation of nonlinear deep resistive networks for energy-based computation — arXiv:2609.07356 — arXiv (en), https://arxiv.org/abs/2609.07356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe4e687d2a4f (Metraipolis archive dc_fe4e687d2a4f, sha256 c8c8f60995abc1ff488bebdf520cfc937bcbc3ac40492628f04fe9f1e34a13e5)
BibTeX
@misc{dcfe4e687d2a4f,
  title = {Fast simulation of nonlinear deep resistive networks for energy-based computation — arXiv:2609.07356},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07356},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe4e687d2a4f; sha256 c8c8f60995abc1ff488bebdf520cfc937bcbc3ac40492628f04fe9f1e34a13e5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep resistive networks are electronic energy-based systems in which computation is performed by the steady-state voltages of nonlinear circuits. Nonlinear devices enable expressive input-output transformations, but make the circuit equilibria costly to compute during simulation and training. Recent coordinate-descent solvers have achieved large speedups over SPICE-class circuit simulators, but only for nonlinearities modeled as ideal-diode models. This mathematical simplification is not sufficient for practical analog circuits. Here we extend coordinate-descent simulation to realistic monotone nonlinearities, including Shockley diodes, antiparallel diode pairs, and piecewise-linear current-voltage characteristics. With neighboring voltages fixed, each node update remains a scalar Kirchhoff-law solve. Single-exponential characteristics admit closed-form Lambert-(W) updates, while more general monotone characteristics can be handled with scalar root-finding methods. Across networks with one to three hidden layers and hidden widths from 64 to 1024, the solver reproduces matched SPICE steady-state voltages with relative $L_1$ errors below $1.1\times10^{-4}$ for 90% of validation samples, while achieving speedups up to $(1.7\times10^3)$. We further train a $1568\times100\times20$ double-Shockley network on MNIST, reaching about 3.0% test error and reducing the per-epoch training time by roughly $4.4\times10^2$. Together, these results establish a practical route to the circuit-level design and training of large-scale analog energy-based systems incorporating realistic nonlinear devices.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.ET).
Categorie arXiv: Emerging Technologies (cs.ET).
Pagina del lavoro: https://arxiv.org/abs/2609.07356 — 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 2026-10-16T15:31:57.835Z dalla pagina https://arxiv.org/catchup/cs.ET/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).