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 2506.08029eess.SYcs.AIcs.LGcs.SY
收藏

使用单步强化学习的分布式电路逆向设计

Inverse Design in Distributed Circuits Using Single-Step Reinforcement Learning

Syracuse University, New York, USA(苏利文大学);Futurewei Technologies Inc., California, USA(未来wei技术公司);University of Notre Dame, Indiana, USA(诺特大学)

Jiayu Li, Masood Mortazavi, Ning Yan, Yihong Ma, Reza Zafarani

AI总结:

针对分布式电路逆向设计中不可微评估、拓扑变化和近连续布局问题,提出 DCIDA 单步强化学习框架,通过联合条件分布与单射映射学习设计采样策略,显著降低设计误差。

摘要:

分布式电路逆向设计的目标是生成满足理想传递函数规格的近最优设计。现有设计探索方法使用涉及人工网格、可微评估流程和特定模板拓扑的策略组合。然而,现实世界的设计实践通常需要不可微评估流程、变化的拓扑以及近连续布局空间。本文提出 DCIDA,这是一种设计探索框架,可为目标传递函数学习近最优的设计采样策略。DCIDA 通过从该策略生成的一组联合训练的条件分布中采样,在一个复合单步动作中决定所有设计因素。利用单射且相互依赖的“映射”,DCIDA 将原始采样设计“动作”转换为唯一等价的物理表示,使该框架能够学习联合“原始”设计决策之间的条件依赖。实验表明,与最先进方法相比,DCIDA 基于 Transformer 的策略网络显著降低了设计误差,并在涉及更复杂传递函数的情况下实现明显更好的拟合。

英文摘要:

The goal of inverse design in distributed circuits is to generate near-optimal designs that meet a desirable transfer function specification. Existing design exploration methods use some combination of strategies involving artificial grids, differentiable evaluation procedures, and specific template topologies. However, real-world design practices often require non-differentiable evaluation procedures, varying topologies, and near-continuous placement spaces. In this paper, we propose DCIDA, a design exploration framework that learns a near-optimal design sampling policy for a target transfer function. DCIDA decides all design factors in a compound single-step action by sampling from a set of jointly-trained conditional distributions generated by the policy. Utilizing an injective interdependent ``map", DCIDA transforms raw sampled design ``actions" into uniquely equivalent physical representations, enabling the framework to learn the conditional dependencies among joint ``raw'' design decisions. Our experiments demonstrate DCIDA's Transformer-based policy network achieves significant reductions in design error compared to state-of-the-art approaches, with significantly better fit in cases involving more complex transfer functions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑