Variational quantum Boltzmann machines

This work presents a novel realization approach to Quantum Boltzmann Machines (QBMs). The preparation of the required Gibbs states, as well as the evaluation of the loss function's analytic gradient is based on Variational Quantum Imaginary Time Evolution, a technique that is typically used for ground state computation. In contrast to existing methods, this implementation facilitates near-term compatible QBM training with gradients of the actual loss function for arbitrary parameterized Hamiltonians which do not necessarily have to be fully-visible but may also include hidden units. The variational Gibbs state approximation is demonstrated with numerical simulations and experiments run on real quantum hardware provided by IBM Quantum. Furthermore, we illustrate the application of this variational QBM approach to generative and discriminative learning tasks using numerical simulation.

[1]  Asja Fischer,et al.  Training Restricted Boltzmann Machines , 2015, KI - Künstliche Intelligenz.

[2]  N. Wiebe,et al.  Tomography and generative training with quantum Boltzmann machines , 2016, 1612.05204.

[3]  E. Knill,et al.  Simulating physical phenomena by quantum networks , 2001, quant-ph/0108146.

[4]  Anirban Narayan Chowdhury,et al.  A Variational Quantum Algorithm for Preparing Quantum Gibbs States , 2020, 2002.00055.

[5]  Erik R. Altman,et al.  Synthesizing credit card transactions , 2019, ICAIF.

[6]  W. Pauli,et al.  Über Gasentartung und Paramagnetismus , 1927 .

[7]  Ying Li,et al.  Theory of variational quantum simulation , 2018, Quantum.

[8]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[9]  Kedar Damle,et al.  Sign-Problem-Free Monte Carlo Simulation of Certain Frustrated Quantum Magnets. , 2015, Physical review letters.

[10]  Yusuke Nomura,et al.  Constructing exact representations of quantum many-body systems with deep neural networks , 2018, Nature Communications.

[11]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[12]  Frits C. R. Spieksma,et al.  Boltzmann Machines , 1995, Artificial Neural Networks.

[13]  W. Magnus.  On the exponential solution of differential equations for a linear operator , 1954 .

[14]  E. Farhi,et al.  A Quantum Approximate Optimization Algorithm Applied to a Bounded Occurrence Constraint Problem , 2014, 1412.6062.

[15]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[16]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[17]  M. Yung,et al.  A quantum–quantum Metropolis algorithm , 2010, Proceedings of the National Academy of Sciences.

[18]  Nathan Wiebe,et al.  Generative training of quantum Boltzmann machines with hidden units , 2019, ArXiv.

[19]  Simona Cocco,et al.  Learning Compositional Representations of Interacting Systems with Restricted Boltzmann Machines: Comparative Study of Lattice Proteins , 2019, Neural Computation.

[20]  Geoffrey E. Hinton,et al.  Phone recognition using Restricted Boltzmann Machines , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[21]  Renato A. Krohling,et al.  Time Series Prediction Using Restricted Boltzmann Machines and Backpropagation , 2015, ITQM.

[22]  Laurent Younes,et al.  Synchronous Boltzmann machines can be universal approximators , 1996 .

[23]  Nicolas Le Roux,et al.  Deep Belief Networks Are Compact Universal Approximators , 2010, Neural Computation.

[24]  ProblemsPer Christian HansenDepartment.  The L-curve and its use in the numerical treatment of inverse problems , 2000 .

[25]  Nathan Killoran,et al.  Quantum generative adversarial networks , 2018, Physical Review A.

[26]  Hong Yao,et al.  Majorana-Time-Reversal Symmetries: A Fundamental Principle for Sign-Problem-Free Quantum Monte Carlo Simulations. , 2016, Physical review letters.

[27]  Yudong Cao,et al.  Realizing Quantum Boltzmann Machines Through Eigenstate Thermalization , 2019, 1903.01359.

[28]  Siu A. Chin,et al.  A fourth-order real-space algorithm for solving local Schrödinger equations , 2001 .

[29]  R. Tibshirani,et al.  Regression shrinkage and selection via the lasso: a retrospective , 2011 .

[30]  Andrew S. Darmawan,et al.  Restricted Boltzmann machine learning for solving strongly correlated quantum systems , 2017, 1709.06475.

[31]  Matthias Troyer,et al.  Computational complexity and fundamental limitations to fermionic quantum Monte Carlo simulations , 2004, Physical review letters.

[32]  S. Golden.  LOWER BOUNDS FOR THE HELMHOLTZ FUNCTION , 1965 .

[33]  Trond Steihaug,et al.  Truncated-newtono algorithms for large-scale unconstrained optimization , 1983, Math. Program..

[34]  H. Yao,et al.  Solving the fermion sign problem in quantum Monte Carlo simulations by Majorana representation , 2014, 1408.2269.

[35]  P Bertet,et al.  Characterization of a two-transmon processor with individual single-shot qubit readout. , 2012, Physical review letters.

[36]  S. Lloyd,et al.  Quantum Algorithm Providing Exponential Speed Increase for Finding Eigenvalues and Eigenvectors , 1998, quant-ph/9807070.

[37]  Ludwig Boltzmann.  Ueber die Natur der Gasmoleküle , 1877 .

[38]  Giacomo Nannicini,et al.  Improving Variational Quantum Optimization using CVaR , 2019, Quantum.

[39]  Adriano M. Pereira,et al.  Restricted Boltzmann Machines for the Prediction of Trends in Financial Time Series , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[40]  Garnet Kin-Lic Chan,et al.  Quantum Imaginary Time Evolution, Quantum Lanczos, and Quantum Thermal Averaging , 2019 .

[41]  J. Cirac,et al.  Restricted Boltzmann machines in quantum physics , 2019, Nature Physics.

[42]  R. Peierls.  On Ising's model of ferromagnetism , 1936, Mathematical Proceedings of the Cambridge Philosophical Society.

[43]  E. Knill,et al.  Quantum algorithms for fermionic simulations , 2000, cond-mat/0012334.

[44]  Fernando G. S. L. Brandão,et al.  Finite Correlation Length Implies Efficient Preparation of Quantum Thermal States , 2016, Communications in Mathematical Physics.

[45]  Yue Sun,et al.  Option Pricing using Quantum Computers , 2019, Quantum.

[46]  Ying Li,et al.  Variational ansatz-based quantum simulation of imaginary time evolution , 2018, npj Quantum Information.

[47]  Hartmut Neven,et al.  Classification with Quantum Neural Networks on Near Term Processors , 2018, 1802.06002.

[48]  D. Poulin,et al.  Sampling from the thermal quantum Gibbs state and evaluating partition functions with a quantum computer. , 2009, Physical review letters.

[49]  John G. Rarity,et al.  Learning models of quantum systems from experiments , 2020, Nature Physics.

[50]  S. Benjamin,et al.  Quantum natural gradient generalised to non-unitary circuits , 2019 .

[51]  G. Brassard,et al.  Quantum Amplitude Amplification and Estimation , 2000, quant-ph/0005055.

[52]  Guido Montúfar,et al.  Restricted Boltzmann Machines: Introduction and Review , 2018, ArXiv.

[53]  Bohyung Han,et al.  Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization , 2017, NIPS.

[54]  J. Besag.  Statistical Analysis of Non-Lattice Data , 1975 .

[55]  Stefan Woerner,et al.  Quantum Generative Adversarial Networks for learning and loading random distributions , 2019, npj Quantum Information.

[56]  J. Gibbs.  Elementary Principles in Statistical Mechanics: Developed with Especial Reference to the Rational Foundation of Thermodynamics , 1902 .

[57]  Geoffrey I. Webb,et al.  Generative and Discriminative Learning , 2017, Encyclopedia of Machine Learning and Data Mining.

[58]  Srinivasan Arunachalam,et al.  Sample-efficient learning of quantum many-body systems , 2020, 2020 IEEE 61st Annual Symposium on Foundations of Computer Science (FOCS).

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

[60]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[61]  F. Verstraete,et al.  Quantum Metropolis sampling , 2009, Nature.

[62]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[63]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[64]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[65]  Hilbert J Kappen,et al.  Learning quantum models from quantum or classical data , 2018, Journal of Physics A: Mathematical and Theoretical.

[66]  Christian Igel,et al.  An Introduction to Restricted Boltzmann Machines , 2012, CIARP.

[67]  Sanjiv Kumar,et al.  On the Convergence of Adam and Beyond , 2018 .

[68]  Roger Melko,et al.  Quantum Boltzmann Machine , 2016, 1601.02036.

[69]  E. Ising.  Beitrag zur Theorie des Ferromagnetismus , 1925 .

[70]  David P. DiVincenzo,et al.  The complexity of stoquastic local Hamiltonian problems , 2006, Quantum Inf. Comput..

[71]  C. Thompson.  Inequality with Applications in Statistical Mechanics , 1965 .

[72]  B. M. Deb,et al.  One dimensional multiple-well oscillators: A time-dependent quantum mechanical approach , 2002 .

[73]  Feng Liu,et al.  Deep Learning Approaches for Link Prediction in Social Network Services , 2013, ICONIP.

[74]  C. Gogolin,et al.  Evaluating analytic gradients on quantum hardware , 2018, Physical Review A.

[75]  Fernando G. S. L. Brandão,et al.  Quantum Gibbs Samplers: The Commuting Case , 2014, Communications in Mathematical Physics.

[76]  Ingo Roth,et al.  Easing the Monte Carlo sign problem , 2019, Science Advances.

[77]  Ilya Sutskever,et al.  On the Convergence Properties of Contrastive Divergence , 2010, AISTATS.

[78]  Kenji Harada,et al.  Symmetry-protected topological order and negative-sign problem for SO(N) bilinear-biquadratic chains , 2013, 1312.2643.

[79]  Thierry Paul,et al.  Quantum computation and quantum information , 2007, Mathematical Structures in Computer Science.