Differentiable learning of quantum circuit Born machines
Authors:
Top Cited Papers
- 19 December 2018
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 98 (6) , 062324
Abstract
Quantum circuit Born machines are generative models which represent the probability distribution of classical dataset as quantum pure states. Computational complexity considerations of the quantum sampling problem suggest that the quantum circuits exhibit stronger expressibility compared to classical neural networks. One can efficiently draw samples from the quantum circuits via projective measurements on qubits. However, similar to the leading implicit generative models in deep learning, such as the generative adversarial networks, the quantum circuits cannot provide the likelihood of the generated samples, which poses a challenge to the training. We devise an efficient gradient-based learning algorithm for the quantum circuit Born machine by minimizing the kerneled maximum mean discrepancy loss. We simulated generative modeling of the BARS-AND-STRIPES dataset and Gaussian mixture distributions using deep quantum circuits. Our experiments show the importance of circuit depth and the gradient-based optimization algorithm. The proposed learning algorithm is runnable on near-term quantum device and can exhibit quantum advantages for probabilistic generative modeling.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (11774398)
- Chinese Academy of Sciences (XDPB0803)
This publication has 34 references indexed in Scilit:
- Kernel methods in machine learningThe Annals of Statistics, 2008
- Fidelity, dynamic structure factor, and susceptibility in critical phenomenaPhysical Review E, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Complexity Limitations on Quantum ComputationJournal of Computer and System Sciences, 1999
- Implementation of the simultaneous perturbation algorithm for stochastic optimizationIEEE Transactions on Aerospace and Electronic Systems, 1998
- Learning representations by back-propagating errorsNature, 1986
- Approximating discrete probability distributions with dependence treesIEEE Transactions on Information Theory, 1968
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951
- On the Asymptotic Distribution of Differentiable Statistical FunctionsThe Annals of Mathematical Statistics, 1947
- Quantenmechanik der Sto vorg ngeThe European Physical Journal A, 1926