A Quantum Extension of Variational Bayes Inference
arXiv:1712.04709 · doi:10.1103/PhysRevA.98.022330
Abstract
Variational Bayes (VB) inference is one of the most important algorithms in machine learning and widely used in engineering and industry. However, VB is known to suffer from the problem of local optima. In this Letter, we generalize VB by using quantum mechanics, and propose a new algorithm, which we call quantum annealing variational Bayes (QAVB) inference. We then show that QAVB drastically improve the performance of VB by applying them to a clustering problem described by a Gaussian mixture model. Finally, we discuss an intuitive understanding on how QAVB works well.
arXiv comment7 pages, 4 figures
References in corpus (15)
- Mixed State Entanglement and Quantum Error Correction
- Variational Inference: A Review for Statisticians
- Quantum algorithm for solving linear systems of equations
- Quantum Annealing in the Transverse Ising Model
- A Quantum Adiabatic Evolution Algorithm Applied to Random Instances of an NP-Complete Problem
- Quantum support vector machine for big data classification
- A Theory of Quantum Error-Correcting Codes
- Quantum Error Correction for Beginners
- Quantum Annealing: A New Method for Minimizing Multidimensional Functions
- Digitized adiabatic quantum computing with a superconducting circuit
- Error corrected quantum annealing with hundreds of qubits
- A scalable control system for a superconducting adiabatic quantum optimization processor
- Reexamining classical and quantum models for the D-Wave One processor
- Temperature scaling law for quantum annealing optimizers
- Deterministic Quantum Annealing Expectation-Maximization Algorithm