arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.00712cs.LG
收藏

利用函数族结构进行模拟电路优化

Exploiting Function-Family Structure in Analog Circuit Optimization

School of Integrated Circuit Science and Engineering, Beihang University(集成电路科学与工程学院,北航);School of Mechatronic Control Engineering, Shenzhen University(机械电子控制工程学院,深大);School of Mathematical and Physical Science, University of Sheffield(数学与物理科学学院,谢菲尔德大学)

Zhuohua Liu, Kaiqi Huang, Qinxin Mei, Yuanqi Hu, Wei W. Xing

AI总结:

本文提出电路先验网络CPN,利用预训练表格模型和直接预期改进方法,在模拟电路优化中实现高精度和高效性能。

摘要:

模拟电路优化通常被框架为在任意光滑函数上的黑箱搜索,但设备物理约束性能映射到结构化的家族中:指数设备定律、有理传输函数和区域依赖动态。现成的高斯过程替代品施加了全局平滑、静态先验,这些与这些区域切换原语不一致,并且在现实样本量(50-100次评估)下可能严重误拟合高度非线性电路。我们证明了预训练的表格模型编码这些原语能够可靠地进行优化,而无需每电路工程。电路先验网络(CPN)结合了表格基础模型(TabPFN v2)和直接预期改进(DEI),在离散后验下精确计算预期改进,而不是高斯近似。在6个电路和25个基线中,结构匹配的先验在小样本情况下达到R²≈0.99,而GP-Matérn在Bandgap上仅达到R²=0.16,提供1.05-3.81倍更高的FoM,同时迭代次数减少3.34-11.89倍,表明从手工制作模型作为先验向系统物理指导结构识别的转变。我们的代码将在论文接受后公开。

英文摘要:

Analog circuit optimization is typically framed as black-box search over arbitrary smooth functions, yet device physics constrains performance mappings to structured families: exponential device laws, rational transfer functions, and regime-dependent dynamics. Off-the-shelf Gaussian-process surrogates impose globally smooth, stationary priors that are misaligned with these regime-switching primitives and can severely misfit highly nonlinear circuits at realistic sample sizes (50--100 evaluations). We demonstrate that pre-trained tabular models encoding these primitives enable reliable optimization without per-circuit engineering. Circuit Prior Network (CPN) combines a tabular foundation model (TabPFN v2) with Direct Expected Improvement (DEI), computing expected improvement exactly under discrete posteriors rather than Gaussian approximations. Across 6 circuits and 25 baselines, structure-matched priors achieve $R^2 \approx 0.99$ in small-sample regimes where GP-Matérn attains only $R^2 = 0.16$ on Bandgap, deliver $1.05$--$3.81\times$ higher FoM with $3.34$--$11.89\times$ fewer iterations, and suggest a shift from hand-crafting models as priors toward systematic physics-informed structure identification. Our code will be made publicly available upon paper acceptance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑