VQEzy: An Open-Source Dataset for Parameter Initialization in Variational Quantum Eigensolvers
This addresses a data bottleneck for researchers in quantum computing, enabling more effective machine learning-based initialization methods for VQEs, though it is incremental as it builds on existing dataset efforts.
The paper tackled the lack of comprehensive datasets for parameter initialization in Variational Quantum Eigensolvers (VQEs) by introducing VQEzy, a large-scale dataset with 12,110 instances across three domains and seven tasks, including full VQE specifications and optimization trajectories.
Variational Quantum Eigensolvers (VQEs) are a leading class of noisy intermediate-scale quantum (NISQ) algorithms, whose performance is highly sensitive to parameter initialization. Although recent machine learning-based initialization methods have achieved state-of-the-art performance, their progress has been limited by the lack of comprehensive datasets. Existing resources are typically restricted to a single domain, contain only a few hundred instances, and lack complete coverage of Hamiltonians, ansatz circuits, and optimization trajectories. To overcome these limitations, we introduce VQEzy, the first large-scale dataset for VQE parameter initialization. VQEzy spans three major domains and seven representative tasks, comprising 12,110 instances with full VQE specifications and complete optimization trajectories. The dataset is available online, and will be continuously refined and expanded to support future research in VQE optimization.