Neural Network Representation of Tensor Network and Chiral States.

We study the representational power of Boltzmann machines (a type of neural network) in quantum many-body systems. We prove that any (local) tensor network state has a (local) neural network representation. The construction is almost optimal in the sense that the number of parameters in the neural network representation is almost linear in the number of nonzero parameters in the tensor network representation. Despite the difficulty of representing (gapped) chiral topological states with local tensor networks, we construct a quasilocal neural network representation for a chiral p-wave superconductor. These results demonstrate the power of Boltzmann machines.

[1]  S. R. Clark,et al.  Unifying neural-network quantum states and correlator product states via tensor networks , 2017, 1710.03545.

[2]  Frank Verstraete,et al.  Matrix product state representations , 2006, Quantum Inf. Comput..

[3]  D. Deng,et al.  Quantum Entanglement in Neural Network States , 2017, 1701.04844.

[4]  N. Read,et al.  Paired states of fermions in two dimensions with breaking of parity and time-reversal symmetries and the fractional quantum Hall effect , 1999, cond-mat/9906453.

[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]  Seung Woo Shin,et al.  Quantum Hamiltonian Complexity , 2014, Found. Trends Theor. Comput. Sci..

[7]  Elina Robeva,et al.  Duality of Graphical Models and Tensor Networks , 2017, Information and Inference: A Journal of the IMA.

[8]  M. B. Hastings,et al.  Locality in Quantum Systems , 2010, 1008.5137.

[9]  F. Verstraete,et al.  Grassmann tensor network states and its renormalization for strongly correlated fermionic and bosonic states , 2010, 1004.2563.

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

[11]  J I Cirac,et al.  Projected entangled-pair states can describe chiral topological states. , 2013, Physical review letters.

[12]  Dong-Ling Deng,et al.  Machine Learning Topological States , 2016, 1609.09060.

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

[14]  Raphael Kaubruegger,et al.  Chiral topological phases from artificial neural networks , 2017, 1710.04713.

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

[16]  Umesh Vazirani,et al.  An area law and sub-exponential algorithm for 1D systems , 2013, 1301.1162.

[17]  M. Fannes,et al.  Finitely correlated states on quantum spin chains , 1992 .

[18]  Nihat Ay,et al.  Refinements of Universal Approximation Results for Deep Belief Networks and Restricted Boltzmann Machines , 2010, Neural Computation.

[19]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

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

[21]  J. Eisert,et al.  Locality of temperature , 2013, 1309.0816.

[22]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[23]  N. Read,et al.  Tensor network trial states for chiral topological phases in two dimensions , 2013, 1307.7726.

[24]  J. Chen,et al.  Equivalence of restricted Boltzmann machines and tensor network states , 2017, 1701.04831.

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

[26]  J. Ignacio Cirac,et al.  Approximating Gibbs states of local Hamiltonians efficiently with projected entangled pair states , 2014, 1406.2973.

[27]  Matthias Troyer,et al.  Solving the quantum many-body problem with artificial neural networks , 2016, Science.

[28]  Yichen Huang,et al.  Classical simulation of quantum many-body systems , 2015 .

[29]  T. Neupert,et al.  Topological Superconductors and Category Theory , 2015, 1506.05805.

[30]  Yichen Huang,et al.  Area law in one dimension: Degenerate ground states and Renyi entanglement entropy , 2014, 1403.0327.

[31]  M. Hastings,et al.  An area law for one-dimensional quantum systems , 2007, 0705.2024.

[32]  Dong-Ling Deng,et al.  Exact Machine Learning Topological States , 2016 .

[33]  L. Duan,et al.  Efficient representation of topologically ordered states with restricted Boltzmann machines , 2018, Physical Review B.

[34]  F. Verstraete,et al.  Matrix product states represent ground states faithfully , 2005, cond-mat/0505140.

[35]  M. B. Hastings,et al.  Solving gapped Hamiltonians locally , 2006 .

[36]  L. Trefethen.  Finite Difference and Spectral Methods for Ordinary and Partial Differential Equations , 1996 .

[37]  Sujie Li,et al.  Boltzmann machines as two-dimensional tensor networks , 2021, Physical Review B.

[38]  Lu-Ming Duan,et al.  Efficient representation of quantum many-body states with deep neural networks , 2017, Nature Communications.