AI RESEARCH
Query-Efficient Quantum Approximate Optimization via Graph-Conditioned Trust Regions
arXiv CS.LG
•
ArXi:2604.24803v1 Announce Type: new In low-depth implementations of the Quantum Approximate Optimization Algorithm (QAOA), the dominant cost is often the number of objective evaluations rather than circuit depth. We Under explicit assumptions on local smoothness, curvature, calibration, and noise, we derive bounds on objective degradation within the trust region, lower bounds on gradient variance, preservation of expected objective ordering under depolarizing noise, and finite-sample coverage guarantees.