Post-variational quantum neural networks
This addresses convergence issues in quantum machine learning for NISQ-era computing, but it appears incremental as it builds on existing variational methods.
The paper tackles the barren plateau problem in variational quantum algorithms by introducing post-variational strategies that shift tunable parameters to classical computers and use ensemble optimization with convex programming, showing empirically that these networks can potentially outperform variational algorithms and match two-layer neural networks.
Hybrid quantum-classical computing in the noisy intermediate-scale quantum (NISQ) era with variational algorithms can exhibit barren plateau issues, causing difficult convergence of gradient-based optimization techniques. In this paper, we discuss "post-variational strategies", which shift tunable parameters from the quantum computer to the classical computer, opting for ensemble strategies when optimizing quantum models. We discuss various strategies and design principles for constructing individual quantum circuits, where the resulting ensembles can be optimized with convex programming. Further, we discuss architectural designs of post-variational quantum neural networks and analyze the propagation of estimation errors throughout such neural networks. Finally, we show that empirically, post-variational quantum neural networks using our architectural designs can potentially provide better results than variational algorithms and performance comparable to that of two-layer neural networks.