A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
Transfer learning of optimal qaoa parameters in combinatorial optimization (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
quant-ph 3representative citing papers
Systematic numerical study of QAOA parameter transfer on heavy-hex Ising models with local cubic terms shows transferred angles from small instances yield improving expectation values up to 49 layers on instances up to 156 qubits, with hardware runs confirming gains up to p=10.
DC-QAOA with CD-mixer ansatz outperforms QAOA for 1d bin packing, showing robustness and high accuracy on a 10-item instance executed on IBM quantum hardware.
citing papers explorer
-
Graph-Conditioned Meta-Optimizer for QAOA Parameter Generation on Multiple Problem Classes
A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
-
Evaluating the Limits of QAOA Parameter Transfer at High-Rounds on Sparse Ising Models With Geometrically Local Cubic Terms
Systematic numerical study of QAOA parameter transfer on heavy-hex Ising models with local cubic terms shows transferred angles from small instances yield improving expectation values up to 49 layers on instances up to 156 qubits, with hardware runs confirming gains up to p=10.
-
Digitized Counter-Diabatic Quantum Optimization for Bin Packing Problem
DC-QAOA with CD-mixer ansatz outperforms QAOA for 1d bin packing, showing robustness and high accuracy on a 10-item instance executed on IBM quantum hardware.