HOLMES: In-Context Failure-Center Localization for High-Dimensional Yield Estimation

2026-08-27

AI Summary

该研究通过将故障中心定位转化为少量样本二分类问题，并结合SVD的各向异性提议和自适应混合方案，解决了高维产量估计中因类别不平衡导致的精度崩溃问题。

Abstract

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}

Problem

• high-sigma yield estimation
• failure center localization
• class imbalance
• importance sampling
• dimensionality

Innovation

• failure-center localization
• few-shot binary classification
• gradient-free inference
• anisotropic proposal
• adaptive mixing scheme