Quantum Optimization for Training Quantum Neural Networks
This addresses a critical bottleneck in quantum machine learning for researchers and practitioners, though it appears incremental as it builds on existing quantum optimization ideas.
The paper tackles the problem of barren plateaus in training quantum neural networks (QNNs) by developing a quantum optimization framework that encodes cost functions onto quantum states, resulting in expected beyond-Grover speedup to mitigate this issue.
Training quantum neural networks (QNNs) using gradient-based or gradient-free classical optimisation approaches is severely impacted by the presence of barren plateaus in the cost landscapes. In this paper, we devise a framework for leveraging quantum optimisation algorithms to find optimal parameters of QNNs for certain tasks. To achieve this, we coherently encode the cost function of QNNs onto relative phases of a superposition state in the Hilbert space of the network parameters. The parameters are tuned with an iterative quantum optimisation structure using adaptively selected Hamiltonians. The quantum mechanism of this framework exploits hidden structure in the QNN optimisation problem and hence is expected to provide beyond-Grover speed up, mitigating the barren plateau issue.