AI 中文总结
HOLMES 将失效中心定位转为少样本二分类，结合 SVD 各向异性提议与命中率自适应混合方案，在 6T SRAM 基准上实现高 sigma 良率估计，相对误差低且加速比高。
AI 中文摘要
高 sigma 良率估计的重要性采样需要从严重不平衡的样本集中定位失效中心。现有的代理辅助方法依赖基于梯度的迭代训练，在极端类别不平衡时是不适定的；模型误差会传播到估计器中，导致高维情况下的精度崩溃。我们将失效中心定位重新表述为少样本二分类：一个先验拟合的表格基础模型在单次前向传播中执行无梯度的上下文内推理，消除了不适定的训练循环。HOLMES（High-sigma Optimal Localization via Manifold Estimation and Sampling，即通过流形估计与采样实现的高 sigma 最优定位）将其与基于 SVD 的各向异性提议相结合，该提议可捕捉失效流形的局部几何结构，还有一个命中率驱动的自适应混合方案，用于在传统自适应方法崩溃的地方稳定重要性权重。在跨越 D=108 到 D=1152 的 6T SRAM 基准测试中，全维基线在某些维度上表现出精度崩溃，最强基线达到 25.8% 的相对误差；在两个最大维度上还额外评估了 PCA+MNIS。HOLMES 在所有五种配置中的相对误差均保持在 5.9% 以内，相较于蒙特卡洛方法实现了最高 58.8 倍的加速。代码可在提供的链接获取。
英文摘要
Importance sampling for high-sigma yield estimation requires locating the failure center from a severely imbalanced sample set. Existing surrogate-assisted methods rely on iterative gradient-based training, ill-posed under extreme class imbalance; model errors propagate into the estimator, causing accuracy collapse in high dimensions. We recast failure-center localization as few-shot binary classification: a prior-fitted tabular foundation model performs gradient-free in-context inference in a single forward pass, eliminating the ill-posed training loop. \textbf{HOLMES} (High-sigma Optimal Localization via Manifold Estimation and Sampling) pairs this with an SVD-based anisotropic proposal that captures the local geometry of the failure manifold, and a hit-rate-driven adaptive mixing scheme that stabilizes importance weights where conventional adaptation collapses. On 6T SRAM benchmarks spanning $D = 108$ to $D = 1{,}152$, full-dimensional baselines exhibit accuracy collapse at some dimension, with the strongest baseline reaching 25.8\% relative error; PCA+MNIS is additionally evaluated at the two largest dimensions. HOLMES remains within 5.9\% across all five configurations with up to $58.8\times$ speedup over Monte Carlo. The code is available on \href{https://github.com/IceLab-JCIE/ICE006-Yield-Holmes}
CommentsPublished in ICCAD 2026
