Metraipolis › archive › dc_06e765cb52a5

SPA: Structure-Preserving Approximation of Gated Activations under FHE — arXiv:2610.32065

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32065
License (as archived)
CC0-1.0
Archived
2026-10-26T20:07:16.680Z
SHA-256 of the archived text
8aa6c2811dacddaf4a80cf179eb7be08d26a3f0f1a5ac584dca8c6c5cca22b15
Stable URL of this page
https://metraipolis.com/documento/dc_06e765cb52a5

How to cite

SPA: Structure-Preserving Approximation of Gated Activations under FHE — arXiv:2610.32065 — arXiv (en), https://arxiv.org/abs/2610.32065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06e765cb52a5 (Metraipolis archive dc_06e765cb52a5, sha256 8aa6c2811dacddaf4a80cf179eb7be08d26a3f0f1a5ac584dca8c6c5cca22b15)
BibTeX
@misc{dc06e765cb52a5,
  title = {SPA: Structure-Preserving Approximation of Gated Activations under FHE — arXiv:2610.32065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06e765cb52a5; sha256 8aa6c2811dacddaf4a80cf179eb7be08d26a3f0f1a5ac584dca8c6c5cca22b15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nonlinear activation evaluation remains a major bottleneck in neural inference under fully homomorphic encryption (FHE). FHE supports efficient addition and multiplication, but lacks native operations for exponential functions, reciprocals, and value-dependent selection. High-degree polynomial approximations on fixed intervals are therefore commonly used to replace nonlinear activations. They can achieve small errors but often incur substantial multiplicative depth and latency. We observe that several widely used nonlinear activations share the algebraic structure $A(x)=xg(x)$ with $g(-x)=1-g(x)$. This class includes GELU, SiLU, fixed-parameter Swish, and the scalar nonlinear branches of GEGLU/SwiGLU. We propose \SPA{} (\emph{Structure-Preserving Approximation}) to exploit this shared structure. \SPA{} retains the exact odd component $x/2$ and approximates only the even residual as a polynomial in $x^2$, yielding a comparison-free arithmetic kernel. This construction removes redundant odd degrees of freedom and enables lower-cost polynomial evaluation at a given error target. Plaintext experiments with Gemma-4-E2B and Llama-3.2-3B show that SPA largely preserves downstream task performance without weight updates. Fixed-interval CKKS benchmarks show favorable error--latency trade-offs. On $[-5,5]$, \SPA{}-balanced achieves a $3.25\times$ speedup over MOAI (ICLR'~26) for erf-GELU with comparable error. On the same interval, \SPA{}-accurate achieves $79.22\%$ lower root mean squared error (RMSE) and a $10.40\times$ speedup over Euston (S\&P'~26) for QuickGELU. For SiLU, \SPA{}-accurate achieves $19.02\%$ lower RMSE and a $2.06\times$ speedup over THOR (CCS'~25).

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.32065 — 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 2026-10-26T19:48:33.257Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).