Search papers, labs, and topics across Lattice.
This paper introduces HOLMES, a novel approach for high-dimensional yield estimation that addresses the challenges of locating failure centers in severely imbalanced sample sets. By reformulating failure-center localization as few-shot binary classification, HOLMES eliminates the need for iterative gradient-based training, which is prone to accuracy collapse in high dimensions. The method achieves remarkable performance, maintaining a relative error of only 5.9% across various configurations while offering up to 58.8 times speedup compared to traditional Monte Carlo methods.
HOLMES achieves a staggering 58.8x speedup in high-dimensional yield estimation while maintaining less than 6% relative error, revolutionizing how we approach failure-center localization.
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}
