Quantum Bayesian Neural Networks
arXiv:2107.09599
Abstract
Quantum machine learning promises great speedups over classical algorithms, but it often requires repeated computations to achieve a desired level of accuracy for its point estimates. Bayesian learning focuses more on sampling from posterior distributions than on point estimation, thus it might be more forgiving in the face of additional quantum noise. We propose a quantum algorithm for Bayesian neural network inference, drawing on recent advances in quantum deep learning, and simulate its empirical performance on several tasks. We find that already for small numbers of qubits, our algorithm approximates the true posterior well, while it does not require any repeated computations and thus fully realizes the quantum speedups.
arXiv comment17 pages, 11 figures
References in corpus (18)
- Quantum Computing in the NISQ era and beyond
- Quantum algorithm for solving linear systems of equations
- Quantum principal component analysis
- Weight Uncertainty in Neural Networks
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Quantum speedup of Monte Carlo methods
- Quantum gradient descent for linear systems and least squares
- Quantum Recommendation Systems
- Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors
- Bayesian Neural Network Priors Revisited
- The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
- BNNpriors: A library for Bayesian neural network inference with different prior distributions
- Repulsive Deep Ensembles are Bayesian
- Function Space Particle Optimization for Bayesian Neural Networks
- Bayesian Deep Learning via Subnetwork Inference
- On Stein Variational Neural Network Ensembles
- Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
- Bayesian machine learning for Boltzmann machine in quantum-enhanced feature spaces