Machine learning holographic mapping by neural network renormalization group

The exact holographic mapping (EHM) provides an explicit duality map between a conformal field theory (CFT) configuration and a massive field propagating on an emergent classical geometry. However, designing the optimal holographic mapping is challenging. Here we introduce the neural network renormalization group as a universal approach to design generic EHM for interacting field theories. Given a field theory action, we train a flow-based hierarchical deep generative neural network to reproduce the boundary field ensemble from uncorrelated bulk field fluctuations. In this way, the neural network develops the optimal renormalization group transformations. Using the machine-designed EHM to map the CFT back to a bulk effective action, we determine the bulk geodesic distance from the residual mutual information. We apply this approach to the complex $\phi^4$ theory in two-dimensional Euclidian spacetime in its critical phase, and show that the emergent bulk geometry matches the three-dimensional hyperbolic geometry.

[1]  J. Preskill,et al.  Holographic quantum error-correcting codes: toy models for the bulk/boundary correspondence , 2015, 1503.06237.

[2]  Yang Qi,et al.  Self-learning Monte Carlo method , 2016, 1610.03137.

[3]  Joseph Polchinski,et al.  Holographic and Wilsonian renormalization groups , 2010, 1010.1264.

[4]  Zhao Yang,et al.  Machine Learning Spatial Geometry from Entanglement Features , 2017, 1709.01223.

[5]  Yingfei Gu,et al.  Holographic duality between $(2+1)$-dimensional quantum anomalous Hall state and $(3+1)$-dimensional topological insulators , 2016, 1605.00570.

[6]  Edward Witten.  Anti-de Sitter Space, Thermal Phase Transition, And Confinement in Gauge Theories , 1998 .

[7]  Yuki Nagai,et al.  Self-learning Monte Carlo method with Behler-Parrinello neural networks , 2018, Physical Review B.

[8]  K. Aoki,et al.  Restricted Boltzmann machines for the long range Ising models , 2016, 1701.00246.

[9]  Yoshihiko Abe,et al.  Gradient flow and the renormalization group , 2018, Progress of Theoretical and Experimental Physics.

[10]  Lei Wang,et al.  Discovering phase transitions with unsupervised learning , 2016, 1606.00318.

[11]  Zhao Yang,et al.  Bidirectional holographic codes and sub-AdS locality , 2015, 1510.03784.

[12]  Xiao-Liang Qi,et al.  Exact holographic mapping in free fermion systems , 2015, 1503.08592.

[13]  K. Wilson.  The renormalization group and critical phenomena , 1983 .

[14]  Matthias Troyer,et al.  Neural-network quantum state tomography , 2018 .

[15]  Vijay Balasubramanian,et al.  Holographic interpretations of the renormalization group , 2012, 1211.1729.

[16]  G. Vidal.  Entanglement renormalization. , 2005, Physical review letters.

[17]  Koji Hashimoto,et al.  Deep learning and holographic QCD , 2018, Physical Review D.

[18]  Tzu-Chieh Wei,et al.  Machine learning of phase transitions in the percolation and XY models. , 2018, Physical review. E.

[19]  Roger G. Melko,et al.  Machine learning vortices at the Kosterlitz-Thouless transition , 2017, 1710.09842.

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

[21]  Marc Henneaux,et al.  Central charges in the canonical realization of asymptotic symmetries: An example from three dimensional gravity , 1986 .

[22]  Joaquin F. Rodriguez-Nieva,et al.  Identifying topological order through unsupervised machine learning , 2018, Nature Physics.

[23]  Cédric Bény,et al.  The renormalization group via statistical inference , 2014, 1402.4949.

[24]  Roger G. Melko,et al.  Learning Thermodynamics with Boltzmann Machines , 2016, ArXiv.

[25]  Xi Dong,et al.  Bulk locality and quantum error correction in AdS/CFT , 2014, 1411.7041.

[26]  Li Huang,et al.  Accelerated Monte Carlo simulations with restricted Boltzmann machines , 2016, 1610.02746.

[27]  Martin Hasenbusch.  The two-dimensional XY model at the transition temperature : a high-precision Monte Carlo study , 2005 .

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

[29]  S. Huber,et al.  Learning phase transitions by confusion , 2016, Nature Physics.

[30]  L. Kadanoff.  Scaling laws for Ising models near T(c) , 1966 .

[31]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[32]  Lei Wang,et al.  Neural Network Renormalization Group , 2018, Physical review letters.

[33]  K. Pinn,et al.  Computing the roughening transition of Ising and solid-on-solid models by BCSOS model matching , 1997 .

[34]  Kazuo Fujikawa,et al.  The gradient flow in λϕ4 theory , 2016, 1601.01578.

[35]  B. Swingle,et al.  Entanglement Renormalization and Holography , 2009, 0905.1317.

[36]  J. Maldacena.  The Large-N Limit of Superconformal Field Theories and Supergravity , 1997, hep-th/9711200.

[37]  Akinori Tanaka,et al.  Deep learning and the AdS/CFT correspondence , 2018, Physical Review D.

[38]  K. Hashimoto.  AdS/CFT correspondence as a deep Boltzmann machine , 2019, Physical Review D.

[39]  Kostas Skenderis.  Lecture notes on holographic renormalization , 2002 .

[40]  Roger G. Melko,et al.  Super-resolving the Ising model with convolutional neural networks , 2018, Physical Review B.

[41]  Zohar Ringel,et al.  Mutual information, neural networks and the renormalization group , 2017, ArXiv.

[42]  Yang Qi,et al.  Self-learning Monte Carlo method: Continuous-time algorithm , 2017, 1705.06724.

[43]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[44]  M. Lüscher.  Trivializing Maps, the Wilson Flow and the HMC Algorithm , 2010 .

[45]  L. Pang,et al.  Regressive and generative neural networks for scalar field theory , 2018, Physical Review D.

[46]  E. Neil,et al.  Nonperturbative Renormalization of Operators in Near-Conformal Systems Using Gradient Flows. , 2018, Physical review letters.

[47]  J. de Boer,et al.  On the holographic renormalization group , 1999 .

[48]  Yang Qi,et al.  Self-learning Monte Carlo method and cumulative update in fermion systems , 2017 .

[49]  Roger G. Melko,et al.  Machine learning phases of matter , 2016, Nature Physics.

[50]  Wen-Cong Gan,et al.  Holography as deep learning , 2017, 1705.05750.

[51]  Zohar Ringel,et al.  Optimal Renormalization Group Transformation from Information Theory , 2018, Physical Review X.

[52]  E. Witten.  Anti-de Sitter space and holography , 1998, hep-th/9802150.

[53]  Olsson.  Monte Carlo analysis of the two-dimensional XY model. II. Comparison with the Kosterlitz renormalization-group equations. , 1995, Physical review. B, Condensed matter.

[54]  A. Polyakov,et al.  Gauge Theory Correlators from Non-Critical String Theory , 1998, hep-th/9802109.

[55]  Masahiro Nozaki,et al.  Holographic geometry of entanglement renormalization in quantum field theories , 2012, 1208.3469.

[57]  Yi-Zhuang You,et al.  Holographic coherent states from random tensor networks , 2017 .