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 2609.05251cs.AI

面向功率GaN HEMTs和逻辑纳米线FETs的统一物理感知量子机器学习框架:以更低误差和更紧密的分组间变异性预测未见过的工艺拆分与保留的几何组合

A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability

Rushat Rai, Yun-Yuan Wang, Autsada Kakaen, Pei-Jie Chang, Doan Viet Nguyen, Yuan-Chieh Chiu, Doldet Tantraviwat, Niall Tumilty, Simon See, Wen-Jay Lee, Tai-Yue … 展开作者

Rushat Rai, Yun-Yuan Wang, Autsada Kakaen, Pei-Jie Chang, Doan Viet Nguyen, Yuan-Chieh Chiu, Doldet Tantraviwat, Niall Tumilty, Simon See, Wen-Jay Lee, Tai-Yue Li, Nan-Yow Chen, Tian-Li Wu

首次发表
浏览论文内容

中文总结 AI 辅助

该研究提出统一RL框架,以GNN为策略、PPO优化,搜索紧凑PQCs用于数据稀缺的器件建模,在HEMTs和NWFETs两类器件的11个目标上,相比经典基线实现更低误差与更紧密分组变异性,验证了RL筛选PQCs作为低OOD误差替代模型的潜力。

中文摘要 AI 辅助

我们提出一种统一强化学习(RL)框架,用于为数据稀缺的器件建模发现紧凑的参数化量子电路(PQCs)。该框架中,经近端策略优化(PPO)优化的图神经网络(GNN)策略,以留一组交叉验证(LOGOCV)在保留的工艺或几何分组上的误差作为奖励,搜索电路架构。与6种经典基线相比,该框架在全部11个目标上达到最低平均绝对误差(MAE);对于HEMTs,其Ioff误差降低59%、VTH分组间变异性收窄81%;对于NWFETs,其VTH、SS、Ioff误差降低84%、Ioff分组间变异性收窄82%。这些结果表明,RL筛选的经典模拟PQCs可作为紧凑替代模型,具备低分布外(OOD)误差和改进的物理一致性,且无需对两种评估器件数据集施加显式物理约束、惩罚项或器件特定方程。

英文摘要

We present a unified reinforcement-learning (RL) framework that discovers compact parametrized quantum circuits (PQCs) for data-scarce device modeling. A graph neural network (GNN) policy optimized by proximal policy optimization (PPO) searches circuit architectures using leave-one-group-out cross-validation (LOGOCV) error on held-out process or geometry groups as the reward. The framework achieves the lowest mean absolute error (MAE) on all 11 targets versus six classical baselines, with 59% lower error (Ioff) and 81% tighter fold variability (VTH) for HEMTs and 84% lower error (VTH, SS, Ioff) and 82% tighter fold variability (Ioff) for NWFETs. These results demonstrate the potential of RL-selected, classically simulated PQCs as compact surrogates with low OOD error and improved physical consistency, despite imposing no explicit physical constraints, penalty terms, or device-specific equations, on the two evaluated device datasets.

发表机构

  • National Yang Ming Chiao Tung University(国立阳明交通大学)
  • NVIDIA AI Technology Center(英伟达人工智能技术中心)
  • Chiang Mai University(清迈大学)
  • National Center for High-performance Computing(国家高速网络与计算中心)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑