Accelerating the training of single-layer binary neural networks using the HHL quantum algorithm
This work addresses the training bottleneck for binary neural networks, offering a hybrid quantum-classical approach that is incremental in improving efficiency.
The paper tackles the compute-intensive training of binary neural networks by using the HHL quantum algorithm to extract useful information from quantum states, which reduces the complexity of finding solutions on classical computers.
Binary Neural Networks are a promising technique for implementing efficient deep models with reduced storage and computational requirements. The training of these is however, still a compute-intensive problem that grows drastically with the layer size and data input. At the core of this calculation is the linear regression problem. The Harrow-Hassidim-Lloyd (HHL) quantum algorithm has gained relevance thanks to its promise of providing a quantum state containing the solution of a linear system of equations. The solution is encoded in superposition at the output of a quantum circuit. Although this seems to provide the answer to the linear regression problem for the training neural networks, it also comes with multiple, difficult-to-avoid hurdles. This paper shows, however, that useful information can be extracted from the quantum-mechanical implementation of HHL, and used to reduce the complexity of finding the solution on the classical side.