Bayesian Deep Learning on a Quantum Computer
This work addresses the problem of uncertainty estimation in deep learning for researchers and practitioners, offering a novel quantum approach that is incremental in combining existing quantum and classical techniques.
The authors tackled the challenge of extending Bayesian methods to deep learning by connecting deep neural networks to Gaussian processes, enabling a quantum algorithm that achieves at least polynomial speedup over classical methods and demonstrating its execution on current quantum computers with noise analysis.
Bayesian methods in machine learning, such as Gaussian processes, have great advantages com-pared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to deep architectures has remained a major challenge. Recent results connected deep feedforward neural networks with Gaussian processes, allowing training without backpropagation. This connection enables us to leverage a quantum algorithm designed for Gaussian processes and develop a new algorithm for Bayesian deep learning on quantum computers. The properties of the kernel matrix in the Gaussian process ensure the efficient execution of the core component of the protocol, quantum matrix inversion, providing an at least polynomial speedup over classical algorithms. Furthermore, we demonstrate the execution of the algorithm on contemporary quantum computers and analyze its robustness with respect to realistic noise models.