Metraipolis › archive › dc_e1af3cb81bdc
Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference — arXiv:2609.15527
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.15527
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:11:50.020Z
- SHA-256 of the archived text
4cb36d3e32943eeb4b6868591605d3576e9e838d321dec46165b68a785c5f7b3- Stable URL of this page
https://metraipolis.com/documento/dc_e1af3cb81bdc
How to cite
Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference — arXiv:2609.15527 — arXiv (en), https://arxiv.org/abs/2609.15527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e1af3cb81bdc (Metraipolis archive dc_e1af3cb81bdc, sha256 4cb36d3e32943eeb4b6868591605d3576e9e838d321dec46165b68a785c5f7b3)
BibTeX
@misc{dce1af3cb81bdc,
title = {Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference — arXiv:2609.15527},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.15527},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e1af3cb81bdc; sha256 4cb36d3e32943eeb4b6868591605d3576e9e838d321dec46165b68a785c5f7b3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on constrained platforms such as mobile and embedded devices. However, analog accelerators are inherently susceptible to noise and non-idealities arising from physical component variations, whose behavior is further sensitive to environmental factors. These effects can significantly degrade inference accuracy. In this work, we conduct a comprehensive experimental study on a representative example of analog hardware to investigate the impact of temperature. We first characterize the behavior of stochastic and systematic non-idealities across a range of operating temperatures. Following this, we compare a set of simulation-based and hardware-based mitigation strategies aimed at improving robustness against temperature-induced performance degradation. Our results suggest that temperature-induced degradation is driven primarily by systematic non-idealities rather than stochastic noise alone. Noise-aware training improves robustness, while hardware-in-the-loop training and temperature-aware calibration provide the strongest accuracy retention across varying thermal conditions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.15527 — 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 2026-10-15T23:54:14.772Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).