A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games
arXiv:2311.10859 · doi:10.22331/q-2025-05-06-1737
Abstract
Recent developments in domains such as non-local games, quantum interactive proofs, and quantum generative adversarial networks have renewed interest in quantum game theory and, specifically, quantum zero-sum games. Central to classical game theory is the efficient algorithmic computation of Nash equilibria, which represent optimal strategies for both players. In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of iterations to -Nash equilibria in the -dimensional spectraplex. In this work, we propose a hierarchy of quantum optimization algorithms that generalize MMWU via an extra-gradient mechanism. Notably, within this proposed hierarchy, we introduce the Optimistic Matrix Multiplicative Weights Update (OMMWU) algorithm and establish its average-iterate convergence complexity as iterations to -Nash equilibria. This quadratic speed-up relative to Jain and Watrous' original algorithm sets a new benchmark for computing -Nash equilibria in quantum zero-sum games.
arXiv comment53 pages, 7 figures, QTML 2023 (Long Talk), Quantum Journal 2025
References in corpus (10)
- Quantum strategies
- Quantum generative adversarial networks
- Toward a general theory of quantum games
- A quantum protocol for cheat-sensitive weak coin flipping
- Parallelized Structures for MIMO FBMC under Strong Channel Frequency Selectivity
- Quantum Interactive Proofs with Competing Provers
- The Impossibility of Efficient Quantum Weak Coin-Flipping
- Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems
- Learning in Quantum Common-Interest Games and the Separability Problem
- No-Regret Learning and Equilibrium Computation in Quantum Games