GuiderNet: A Meta-Learning Framework for Optimizing Quantum Circuit Geometry and Mitigating Barren Plateaus

Abstract: Variational Quantum Algorithms (VQAs) offer potential for near-term quantum advantage but face challenges from barren plateaus, where gradients vanish, and poorly conditioned optimization landscapes. We introduce GuiderNet, a meta-learning framework that conditions Parameterized Quantum Circuits (PQCs) using data-dependent parameter shifts aimed at minimizing the log condition number of the Fubini-Study metric tensor. Implemented as a classical neural network, GuiderNet is meta-trained to guide PQC parameters into geometrically favorable regions and is embedded within hybrid quantum-classical pipelines to steer both initialization and adaptive modulation during training. Applied to the Kaggle Diabetes classification task, GuiderNet reduces cumulative training loss by over 5x, improves test accuracy from 75.3% to 98.6%, and increases the minority-class F1 score from 0.67 to 0.95. It also suppresses gradient explosion and stabilizes parameter updates, enabling smoother and more robust optimization. These results demonstrate that geometric meta-conditioning can mitigate barren plateaus and ill-conditioning, providing a scalable approach to enhance trainability and generalization in quantum machine learning.