DiffQ: Unified Parameter Initialization for Variational Quantum Algorithms via Diffusion Models

V ariational Quantum Algorithms (VQAs) [1] have emerged as leading methods for the noisy intermediate-scale quantum (NISQ) era [2]. By combining limited quantum resources with classical optimizers, they reduce reliance on fault-tolerant devices while offering resilience to noise [1], low circuit complexity [3], and design flexibility [4]. VQAs have already demonstrated success in quantum physics, chemistry, and materials science [5-7]. Despite this promise, their scalability remains a central challenge: as system size increases, optimization landscapes flatten exponentially [8], leading to vanishing gradients and poor convergence. Parameter initialization has therefore become a critical strategy [9], reshaping the landscape to enhance trainability and mitigate suboptimal convergence. Recent deep learning-based initialization methods [10-13] define the state of the art, yet they remain task-specific, depend on limited datasets, and are typically validated in narrow settings, constraining their generalizability across diverse VQA applications.