Metraipolis › archive › dc_710b7dfd1437

NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory — arXiv:2608.02700

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.02700
License (as archived): CC0-1.0
Archived: 2026-10-31T12:17:42.210Z
SHA-256 of the archived text: 39089f3804df650a6f53eb3d160c82101c66d42f4c4468e4fe7ec263bffb7ba0
Stable URL of this page: https://metraipolis.com/documento/dc_710b7dfd1437

How to cite

NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory — arXiv:2608.02700 — arXiv (en), https://arxiv.org/abs/2608.02700 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_710b7dfd1437 (Metraipolis archive dc_710b7dfd1437, sha256 39089f3804df650a6f53eb3d160c82101c66d42f4c4468e4fe7ec263bffb7ba0)

BibTeX

@misc{dc710b7dfd1437,
  title = {NANQ: Noise-Floor-Aware Mixed-Precision Non-Uniform Quantization for Analog Compute-in-Memory — arXiv:2608.02700},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02700},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_710b7dfd1437; sha256 39089f3804df650a6f53eb3d160c82101c66d42f4c4468e4fe7ec263bffb7ba0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02700. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Analog compute-in-memory (CIM) enables energy-efficient neural network inference, but device variation and read noise can severely degrade low-bit quantized models. Existing CIM-oriented quantization methods mainly minimize ideal quantization error, ignoring the hardware noise floor and thus causing inefficient precision allocation. We propose NANQ, a noise-aware mixed-precision non-uniform quantization framework for analog CIM. NANQ models magnitude-dependent weight noise from measured responses of an eFlash CIM array and converts the noise profile into an adaptive quantization density, assigning finer resolution to low-noise regions while avoiding ineffective precision in noise-dominated regions. It further assigns layer-wise bit-widths by identifying each layer's precision saturation point under hardware noise using a unified threshold. On-chip experiments on an eFlash CIM SoC show that, under 2-bit weight-magnitude quantization, NANQ improves vision-model accuracy by 8.05 percentage points and reduces language-model PPL by 54.7% on average over PowerQuant. Mixed-precision NANQ captures most of the gains obtainable from additional quantization resources with only 3.2-3.8 equivalent bits.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02700 — 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 2026-10-31T12:05:52.941Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).