Quantum Boltzmann Machine

Inspired by the success of Boltzmann Machines based on classical Boltzmann distribution, we propose a new machine learning approach based on quantum Boltzmann distribution of a transverse-field Ising Hamiltonian. Due to the non-commutative nature of quantum mechanics, the training process of the Quantum Boltzmann Machine (QBM) can become nontrivial. We circumvent the problem by introducing bounds on the quantum probabilities. This allows us to train the QBM efficiently by sampling. We show examples of QBM training with and without the bound, using exact diagonalization, and compare the results with classical Boltzmann training. We also discuss the possibility of using quantum annealing processors like D-Wave for QBM training and application.

[1]  Hiroshi Nagaoka,et al.  An information geometrical approach to the mean-field approximation for quantum Ising spin models , 2008 .

[2]  M. W. Johnson,et al.  Thermally assisted quantum annealing of a 16-qubit problem , 2013, Nature Communications.

[3]  N. J. Cohen,et al.  Higher-Order Boltzmann Machines , 1986 .

[4]  S. Lloyd,et al.  Quantum algorithms for supervised and unsupervised machine learning , 2013, 1307.0411.

[5]  Karoline Wiesner,et al.  Quantum mechanics can reduce the complexity of classical models , 2011, Nature Communications.

[6]  Geoffrey E. Hinton,et al.  OPTIMAL PERCEPTUAL INFERENCE , 1983 .

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

[8]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[9]  Masoud Mohseni,et al.  Computational Role of Multiqubit Tunneling in a Quantum Annealer , 2015 .

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

[11]  Hartmut Neven,et al.  Training a Large Scale Classifier with the Quantum Adiabatic Algorithm , 2009, ArXiv.

[12]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[13]  M. W. Johnson,et al.  Experimental investigation of an eight-qubit unit cell in a superconducting optimization processor , 2010, 1004.1628.

[14]  Geoffrey E. Hinton,et al.  Modeling pixel means and covariances using factorized third-order boltzmann machines , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  M. W. Johnson,et al.  Entanglement in a Quantum Annealing Processor , 2014, 1401.3500.

[16]  W. Macready,et al.  Image recognition with an adiabatic quantum computer I. Mapping to quadratic unconstrained binary optimization , 2008, 0804.4457.

[17]  Daniel A. Lidar,et al.  Evidence for quantum annealing with more than one hundred qubits , 2013, Nature Physics.

[18]  Geoffrey E. Hinton,et al.  Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines , 2010, Neural Computation.

[19]  M. Amin.  Searching for quantum speedup in quasistatic quantum annealers , 2015, 1503.04216.

[20]  Vasil S. Denchev,et al.  Computational multiqubit tunnelling in programmable quantum annealers , 2015, Nature Communications.

[21]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[22]  Yoshua Bengio,et al.  On the Challenges of Physical Implementations of RBMs , 2013, AAAI.

[23]  Misha Denil.  Toward the Implementation of a Quantum RBM , 2011 .

[24]  M. Benedetti,et al.  Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning , 2015, 1510.07611.

[25]  Rupak Biswas,et al.  Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models , 2016, 1609.02542.

[26]  Tapani Raiko,et al.  NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning , 2011 .

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

[28]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[29]  M. W. Johnson,et al.  Quantum annealing with manufactured spins , 2011, Nature.

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

[31]  Daniel A. Lidar,et al.  Experimental signature of programmable quantum annealing , 2012, Nature Communications.

[32]  Geoffrey E. Hinton,et al.  Modeling image patches with a directed hierarchy of Markov random fields , 2007, NIPS.

[33]  Ashish Kapoor,et al.  Quantum deep learning , 2014, Quantum Inf. Comput..

[34]  Daniel A. Lidar,et al.  Quantum adiabatic machine learning , 2011, Quantum Inf. Process..