Generative Tensor Network Classification Model for Supervised Machine Learning

Tensor network (TN) has recently triggered extensive interests in developing machine-learning models in quantum many-body Hilbert space. Here we purpose a generative TN classification (GTNC) approach for supervised learning. The strategy is to train the generative TN for each class of the samples to construct the classifiers. The classification is implemented by comparing the distance in the many-body Hilbert space. The numerical experiments by GTNC show impressive performance on the MNIST and Fashion-MNIST dataset. The testing accuracy is competitive to the state-of-the-art convolutional neural network while higher than the naive Bayes classifier (a generative classifier) and support vector machine. Moreover, GTNC is more efficient than the existing TN models that are in general discriminative. By investigating the distances in the many-body Hilbert space, we find that (a) the samples are naturally clustering in such a space; and (b) bounding the bond dimensions of the TN's to finite values corresponds to removing redundant information in the image recognition. These two characters make GTNC an adaptive and universal model of excellent performance.

[1]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

[2]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[3]  Lei Wang,et al.  Differentiable Learning of Quantum Circuit Born Machine , 2018, Physical Review A.

[4]  Gang Su,et al.  Machine learning by unitary tensor network of hierarchical tree structure , 2017, New Journal of Physics.

[5]  F. Verstraete,et al.  Matrix product states, projected entangled pair states, and variational renormalization group methods for quantum spin systems , 2008, 0907.2796.

[6]  Soonwon Choi,et al.  Quantum convolutional neural networks , 2018, Nature Physics.

[7]  Lei Wang,et al.  Tree Tensor Networks for Generative Modeling , 2019, Physical Review B.

[8]  W. Marsden.  I and J , 2012 .

[9]  J. Mercer.  Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .

[10]  F. S. Prout.  Philosophical Transactions of the Royal Society of London , 2009, The London Medical Journal.

[11]  Ben Calderhead,et al.  Advances in Neural Information Processing Systems 29 , 2016 .

[12]  Roman Orus,et al.  A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States , 2013, 1306.2164.

[13]  Jing Chen,et al.  Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines , 2017, Entropy.

[14]  G. Vidal,et al.  Infinite time-evolving block decimation algorithm beyond unitary evolution , 2008 .

[15]  F. Verstraete,et al.  Renormalization and tensor product states in spin chains and lattices , 2009, 0910.1130.

[16]  Keisuke Fujii,et al.  Quantum circuit learning , 2018, Physical Review A.

[17]  Ronald de Wolf,et al.  Guest Column: A Survey of Quantum Learning Theory , 2017, SIGA.

[18]  Ryan Babbush,et al.  The theory of variational hybrid quantum-classical algorithms , 2015, 1509.04279.

[19]  R. A. Leibler,et al.  On Information and Sufficiency , 1951 .

[20]  Jun Wang,et al.  Unsupervised Generative Modeling Using Matrix Product States , 2017, Physical Review X.

[21]  Maria Schuld,et al.  Quantum Machine Learning in Feature Hilbert Spaces. , 2018, Physical review letters.

[22]  Cheng Peng,et al.  Tensor Network Contractions: Methods and Applications to Quantum Many-Body Systems , 2020 .

[23]  G. Evenbly,et al.  Tensor Network States and Geometry , 2011, 1106.1082.

[24]  Jiangping Hu,et al.  Learning and Inference on Generative Adversarial Quantum Circuits , 2018, Physical Review A.

[25]  U. Schollwoeck.  The density-matrix renormalization group in the age of matrix product states , 2010, 1008.3477.

[26]  F. Petruccione,et al.  An introduction to quantum machine learning , 2014, Contemporary Physics.

[27]  Lukasz Cincio,et al.  Multiscale entanglement renormalization ansatz in two dimensions: quantum Ising model. , 2007, Physical review letters.

[28]  HighWire Press.  Philosophical Transactions of the Royal Society of London , 1781, The London Medical Journal.

[29]  J. Cirac,et al.  Neural-Network Quantum States, String-Bond States, and Chiral Topological States , 2017, 1710.04045.

[30]  Seth Lloyd,et al.  Quantum algorithm for data fitting. , 2012, Physical review letters.

[31]  Jacob biamonte,et al.  Quantum machine learning , 2016, Nature.

[32]  White,et al.  Density matrix formulation for quantum renormalization groups. , 1992, Physical review letters.

[33]  Masoud Mohseni,et al.  Quantum support vector machine for big feature and big data classification , 2013, Physical review letters.

[34]  Masashi Sugiyama,et al.  Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives , 2017, Found. Trends Mach. Learn..

[35]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[36]  Christopher T. Chubb,et al.  Hand-waving and interpretive dance: an introductory course on tensor networks , 2016, 1603.03039.

[37]  Subhash C. Kak,et al.  On Quantum Neural Computing , 1995, Inf. Sci..

[38]  J. I. Latorre,et al.  Scaling of entanglement support for matrix product states , 2007, 0712.1976.

[39]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[40]  Max Tegmark,et al.  Why Does Deep and Cheap Learning Work So Well? , 2016, Journal of Statistical Physics.

[41]  Chu Guo,et al.  Matrix product operators for sequence-to-sequence learning , 2018, Physical Review E.

[42]  Maria Schuld,et al.  Machine learning in quantum spaces , 2019, Nature.

[43]  K. Birgitta Whaley,et al.  Towards quantum machine learning with tensor networks , 2018, Quantum Science and Technology.

[44]  Alejandro Perdomo-Ortiz,et al.  A generative modeling approach for benchmarking and training shallow quantum circuits , 2018, npj Quantum Information.