# High-Dimensional Yield Estimation using Shrinkage Deep Features and Maximization of Integral Entropy Reduction

arXiv: https://arxiv.org/abs/2212.02100 · HTML: https://mlsanity.com/paper/2212.02100/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 15 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 1 of 1)

- [Deep Kernel Learning](https://mlsanity.com/paper/1511.02222/) (2015)

## Built on by (most cited first, 3 of 3)

- [Seeking the Yield Barrier: High-Dimensional SRAM Evaluation Through Optimal Manifold](https://mlsanity.com/paper/2307.15773/) (2023)
- [Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits](https://mlsanity.com/paper/2405.07971/) (2024)
- [Breaking the Tuning Barrier: Zero-Hyperparameters Yield Multi-Corner Analysis Via Learned Priors](https://mlsanity.com/paper/2603.13092/) (2026)

## Abstract (arXiv)

Despite the fast advances in high-sigma yield analysis with the help of machine learning techniques in the past decade, one of the main challenges, the curse of dimensionality, which is inevitable when dealing with modern large-scale circuits, remains unsolved. To resolve this challenge, we propose an absolute shrinkage deep kernel learning, ASDK, which automatically identifies the dominant process variation parameters in a nonlinear-correlated deep kernel and acts as a surrogate model to emulate the expensive SPICE simulation. To further improve the yield estimation efficiency, we propose a novel maximization of approximated entropy reduction for an efficient model update, which is also enhanced with parallel batch sampling for parallel computing, making it ready for practical deployment. Experiments on SRAM column circuits demonstrate the superiority of ASDK over the state-of-the-art (SOTA) approaches in terms of accuracy and efficiency with up to 10.3x speedup over SOTA methods.