Learning to Learn with Quantum Optimization via Quantum Neural Networks
This work addresses a critical bottleneck in quantum optimization for combinatorial problems, offering a scalable solution for the NISQ era, though it is incremental as it builds on existing QAOA and quantum neural network methods.
The paper tackles the challenge of parameter optimization in Quantum Approximate Optimization Algorithms (QAOA), which is hindered by rugged energy landscapes and hardware noise, by introducing a quantum meta-learning framework that combines Quantum Long Short-Term Memory (QLSTM) architectures with QAOA. The result shows that QLSTM-based optimizers converge faster and achieve higher approximation ratios on benchmarks like Max-Cut and Sherrington-Kirkpatrick models, reducing iterations for convergence.
Quantum Approximate Optimization Algorithms (QAOA) promise efficient solutions to classically intractable combinatorial optimization problems by harnessing shallow-depth quantum circuits. Yet, their performance and scalability often hinge on effective parameter optimization, which remains nontrivial due to rugged energy landscapes and hardware noise. In this work, we introduce a quantum meta-learning framework that combines quantum neural networks, specifically Quantum Long Short-Term Memory (QLSTM) architectures, with QAOA. By training the QLSTM optimizer on smaller graph instances, our approach rapidly generalizes to larger, more complex problems, substantially reducing the number of iterations required for convergence. Through comprehensive benchmarks on Max-Cut and Sherrington-Kirkpatrick model instances, we demonstrate that QLSTM-based optimizers converge faster and achieve higher approximation ratios compared to classical baselines, thereby offering a robust pathway toward scalable quantum optimization in the NISQ era.