Ferroelectric Compute-in-Memory Framework for Solving Pure and Mixed Strategy Nash Equilibrium
IEEE Transactions on Circuits and Systems I: Regular Papers · 2025-10 · 72 (10) · 5531-5544
DOI: 10.1109/tcsi.2025.3548871 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems I: Regular Papers, 2025-10. Verfasst von Yu Qian und 8 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Sino-German Center for Research Promotion (SGC) Cooperation Project.
Abstract (Originalsprache)
Nash equilibrium (NE) is a key concept in game theory, but verifying its existence is NP-complete. Recent advancements proposed quantum NE solvers that identify pure strategy NE solutions (binary solutions) by integrating slack terms into the objective function, known as slack-quadratic unconstrained binary optimization (S-QUBO). However, S-QUBO alters the objective function and can lead to incorrect solutions. Additionally, current solvers only find a limited number of pure strategy NE solutions and cannot address mixed strategy NE (decimal solutions), leaving many solutions unexplored. In this work, we propose C-Nash, a novel ferroelectric compute-in-memory (CiM) framework capable of efficiently addressing both pure and mixed strategy NE solutions. C-Nash consists of 1) a transformation method that transforms quadratic optimization into a MAX-QUBO form without incorporating additional slack variables, thus avoiding objective function changes; 2) A ferroelectric FET (FeFET) based CiM bi-crossbar structure and winner-takes-all (WTA) tree for accelerating the MAX-QUBO form in a single iteration; 3) An efficient operation flow including a rank-based QUBO reformulation algorithm that simplifies the QUBO matrices to reduce hardware overhead, and a two-phase based simulated annealing (SA) logic for finding NE solutions; 4) A FeFET-based crossbar macro for experimental demonstration. Experimental results show that C-Nash increases the success rate for identifying NE solutions by 68.6% while saving $3\times $ in chip size. Furthermore, C-Nash can find all pure and mixed NE solutions, unlike D-Wave based quantum approaches which only find some pure strategy NE solutions. Additionally, C-Nash significantly reduces the time-to-solution by up to $157.9\times $ / $79.0\times $ compared to D-Wave 2000 Q6 and D-Wave Advantage 4.1, respectively.
Förderung
- National Natural Science Foundation of China
- Sino-German Center for Research Promotion (SGC) Cooperation Project
Zitieren
APA
Qian, Y., Huang, D., Vardar, A., Laleni, N., Zhou, M., Ni, K., Kämpfe, T., Zhuo, C., & Yin, X. (2025). Ferroelectric Compute-in-Memory Framework for Solving Pure and Mixed Strategy Nash Equilibrium. IEEE Transactions on Circuits and Systems I: Regular Papers, 72(10), 5531-5544. https://doi.org/10.1109/tcsi.2025.3548871
Vancouver
Qian Y, Huang D, Vardar A, Laleni N, Zhou M, Ni K, et al. Ferroelectric Compute-in-Memory Framework for Solving Pure and Mixed Strategy Nash Equilibrium. IEEE Transactions on Circuits and Systems I: Regular Papers. 2025;72(10):5531-5544. doi:10.1109/tcsi.2025.3548871
BibTeX
@article{Qian2025,
author = {Qian, Yu and Huang, Ding and Vardar, Alptekin and Laleni, Nellie and Zhou, Min and Ni, Kai and Kämpfe, Thomas and Zhuo, Cheng and Yin, Xunzhao},
title = {Ferroelectric Compute-in-Memory Framework for Solving Pure and Mixed Strategy Nash Equilibrium},
journal = {IEEE Transactions on Circuits and Systems I: Regular Papers},
year = {2025},
volume = {72},
number = {10},
pages = {5531--5544},
doi = {10.1109/tcsi.2025.3548871}
}
EUVIMED