Learning Algebraic Models of Quantum Entanglement

We give a thorough overview of supervised learning and network design for learning membership on algebraic varieties via deep neural networks. We show how artificial neural networks can be trained to predict the entanglement type for quantum states. We give examples for detecting degenerate states, as well as border rank classification for up to 5 binary qubits and 3 qutrits (ternary qubits).

[1]  Corrado Segre.  Sulle corrispondenze quadrilineari tra forme di 1a specie e su alcune loro rappresentazioni spaziali , 1921 .

[2]  Donald F. Specht,et al.  Generation of Polynomial Discriminant Functions for Pattern Recognition , 1967, IEEE Trans. Electron. Comput..

[3]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  Grazia Lotti,et al.  O(n2.7799) Complexity for n*n Approximate Matrix Multiplication , 1979, Inf. Process. Lett..

[6]  Victor G. Kac,et al.  Some remarks on nilpotent orbits , 1980 .

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  G. Palm.  Warren McCulloch and Walter Pitts: A Logical Calculus of the Ideas Immanent in Nervous Activity , 1986 .

[9]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[11]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[12]  G. J. Gibson,et al.  On the decision regions of multilayer perceptrons , 1990, Proc. IEEE.

[13]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[14]  Tarun Khanna,et al.  Foundations of neural networks , 1990 .

[15]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[16]  Joydeep Ghosh,et al.  Approximation of multivariate functions using ridge polynomial networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[17]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[18]  Sun-Yuan Kung,et al.  Generalized perceptron networks with nonlinear discriminant functions , 1992 .

[19]  V. Rao Vemuri,et al.  Artificial neural networks: Concepts and control applications , 1992 .

[20]  I. M. Gelʹfand,et al.  Discriminants, Resultants, and Multidimensional Determinants , 1994 .

[21]  Joydeep Ghosh,et al.  Ridge polynomial networks , 1995, IEEE Trans. Neural Networks.

[22]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[23]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[24]  P. Wilson,et al.  DISCRIMINANTS, RESULTANTS AND MULTIDIMENSIONAL DETERMINANTS (Mathematics: Theory and Applications) , 1996 .

[25]  Jerzy Weyman,et al.  Singularities of hyperdeterminants , 1996 .

[26]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[27]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[28]  Peter L. Bartlett,et al.  Neural Network Learning - Theoretical Foundations , 1999 .

[29]  J. Cirac,et al.  Three qubits can be entangled in two inequivalent ways , 2000, quant-ph/0005115.

[30]  Jean-Luc Brylinski.  Algebraic measures of entanglement , 2000 .

[31]  G. Dreyfus,et al.  Réseaux de neurones - Méthodologie et applications , 2002 .

[32]  B. Moor,et al.  Four qubits can be entangled in nine different ways , 2001, quant-ph/0109033.

[33]  Akimasa Miyake,et al.  Multipartite entanglement and hyperdeterminants , 2002, Quantum Inf. Comput..

[34]  Karl Rihaczek,et al.  1. WHAT IS DATA MINING? , 2019, Data Mining for the Social Sciences.

[35]  Hong-Xing Li,et al.  INTERPOLATION FUNCTIONS OF FEEDFORWARD NEURAL NETWORKS , 2003 .

[36]  A. Miyake.  Classification of multipartite entangled states by multidimensional determinants , 2002, quant-ph/0206111.

[37]  Sung-Kwun Oh,et al.  Polynomial neural networks architecture: analysis and design , 2003, Comput. Electr. Eng..

[38]  Victoria Hernández-Mederos,et al.  Sampling points on regular parametric curves with control of their distribution , 2003, Comput. Aided Geom. Des..

[39]  J. Luque,et al.  Polynomial invariants of four qubits , 2002, quant-ph/0212069.

[40]  Akimasa Miyake,et al.  Multipartite entanglement in 2 x 2 x n quantum systems , 2003, quant-ph/0307067.

[41]  F. Verstraete,et al.  Multipartite entanglement in 2x2xn quantum systems (9 pages) , 2004 .

[42]  J. Luque,et al.  Algebraic invariants of five qubits , 2005, quant-ph/0506058.

[43]  A. Osterloh,et al.  ENTANGLEMENT MONOTONES AND MAXIMALLY ENTANGLED STATES IN MULTIPARTITE QUBIT SYSTEMS , 2005, quant-ph/0506073.

[44]  Ong Hong Choon,et al.  Non Linear Approximations using Multi-layered Perceptions and Polynomial Regressions , 2006 .

[45]  F. J. Sainz,et al.  Constructive approximate interpolation by neural networks , 2006 .

[46]  Oleg Chterental,et al.  Normal Forms and Tensor Ranks of Pure States of Four Qubits , 2006 .

[47]  Chris Peterson,et al.  Induction for secant varieties of Segre varieties , 2006, math/0607191.

[48]  Willem A. de Graaf,et al.  Secant Dimensions of Minimal Orbits: Computations and Conjectures , 2007, Exp. Math..

[49]  G. Ottaviani,et al.  On the Alexander–Hirschowitz theorem , 2007, math/0701409.

[50]  Vin de Silva,et al.  Tensor rank and the ill-posedness of the best low-rank approximation problem , 2006, math/0607647.

[51]  Bernd Sturmfels,et al.  The hyperdeterminant and triangulations of the 4-cube , 2006, Math. Comput..

[52]  N. K. Langford,et al.  Experimentally generating and tuning robust entanglement between photonic qubits , 2008, 0802.3161.

[53]  Wenhu Xu,et al.  Efficient generation of multi-photon W states by joint-measurement , 2008 .

[54]  N. Wallach,et al.  All maximally entangled four-qubit states , 2010, 1006.0036.

[55]  Isaac L. Chuang,et al.  Quantum Computation and Quantum Information (10th Anniversary edition) , 2011 .

[56]  Giansalvo Cirrincione,et al.  Neural-Based Orthogonal Data Fitting: The EXIN Neural Networks , 2010 .

[57]  J. Landsberg.  Tensors: Geometry and Applications , 2011 .

[58]  Elizabeth C. Behrman,et al.  Dynamic learning of pairwise and three-way entanglement , 2011, 2011 Third World Congress on Nature and Biologically Inspired Computing.

[59]  Jean-Gabriel Luque,et al.  Geometric descriptions of entangled states by auxiliary varieties , 2012, 1204.6375.

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

[61]  Lin Chen,et al.  Proof of the Gour-Wallach conjecture , 2013, 1308.1306.

[62]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[63]  Jean-Gabriel Luque,et al.  Singularity of type D4 arising from four-qubit systems , 2013, 1312.0639.

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

[65]  Giorgio Ottaviani,et al.  An Algorithm For Generic and Low-Rank Specific Identifiability of Complex Tensors , 2014, SIAM J. Matrix Anal. Appl..

[66]  Maria Schuld,et al.  The quest for a Quantum Neural Network , 2014, Quantum Information Processing.

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

[68]  F. Holweck,et al.  Entanglement of four qubit systems: A geometric atlas with polynomial compass I (the finite world) , 2013, 1306.6816.

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

[70]  L. Oeding,et al.  Four Lectures on Secant Varieties , 2013, 1309.4145.

[71]  S. Lloyd,et al.  Quantum principal component analysis , 2013, Nature Physics.

[72]  Anmer Daskin.  Quantum Principal Component Analysis , 2015 .

[73]  Marek Sawerwain,et al.  Detecting Entanglement in Quantum Systems with Artificial Neural Network , 2015, ACIIDS.

[74]  Ian H. Witten,et al.  Data Mining, Fourth Edition: Practical Machine Learning Tools and Techniques , 2016 .

[75]  F. Holweck,et al.  Entanglement of four-qubit systems: a geometric atlas with polynomial compass II (the tame world) , 2016, 1606.05569.

[76]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[77]  Hamza Jaffali,et al.  Grover’s algorithm and the secant varieties , 2016, Quantum Inf. Process..

[78]  Hamza Jaffali,et al.  Three-qutrit entanglement and simple singularities , 2016, 1606.05537.

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

[80]  Timothy Dozat,et al.  Incorporating Nesterov Momentum into Adam , 2016 .

[81]  J. M. Landsberg,et al.  Geometry and Complexity Theory , 2017 .

[82]  Liwei Wang,et al.  The Expressive Power of Neural Networks: A View from the Width , 2017, NIPS.

[83]  Bingjie Wang.  Learning to Detect Entanglement , 2017 .

[84]  Lishen. Govender,et al.  Determination of quantum entanglement concurrence using multilayer perceptron neural networks. , 2017 .

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

[86]  Man-Hong Yung,et al.  Transforming Bell’s inequalities into state classifiers with machine learning , 2017, npj Quantum Information.

[87]  Yu-Bo Sheng,et al.  Distributed secure quantum machine learning. , 2017, Science bulletin.

[88]  F. Holweck,et al.  Hyperdeterminants from the $E_8$ Discriminant , 2018, 1810.05857.

[89]  Rohit Raturi.  Large Data Analysis via Interpolation of Functions: Interpolating Polynomials vs Artificial Neural Networks , 2018 .

[90]  Man-Hong Yung,et al.  Transforming Bell’s inequalities into state classifiers with machine learning , 2018 .

[91]  Yimin Wei,et al.  Geometric measures of entanglement in multipartite pure states via complex-valued neural networks , 2018, Neurocomputing.

[92]  Richard Berkovits,et al.  Extracting many-particle entanglement entropy from observables using supervised machine learning , 2018, Physical Review B.

[93]  Bernd Sturmfels,et al.  Learning algebraic varieties from samples , 2018, Revista Matemática Complutense.

[94]  Stanislav Fort,et al.  Adaptive quantum state tomography with neural networks , 2018, npj Quantum Information.

[95]  Paul J. Scott,et al.  Curvature based sampling of curves and surfaces , 2018, Comput. Aided Geom. Des..

[96]  S. Bose,et al.  Machine-Learning-Assisted Many-Body Entanglement Measurement. , 2017, Physical review letters.

[97]  Mikhail Belkin,et al.  Reconciling modern machine learning and the bias-variance trade-off , 2018, ArXiv.

[98]  Jun Li,et al.  Separability-entanglement classifier via machine learning , 2017, Physical Review A.

[99]  Xi Cheng,et al.  Polynomial Regression As an Alternative to Neural Nets , 2018, ArXiv.

[100]  Mikhail Belkin,et al.  Reconciling modern machine-learning practice and the classical bias–variance trade-off , 2018, Proceedings of the National Academy of Sciences.

[101]  Hamza Jaffali,et al.  Quantum entanglement involved in Grover’s and Shor’s algorithms: the four-qubit case , 2018, Quantum Information Processing.

[102]  Nicolai Friis,et al.  Optimizing Quantum Error Correction Codes with Reinforcement Learning , 2018, Quantum.

[103]  Joan Bruna,et al.  On the Expressive Power of Deep Polynomial Neural Networks , 2019, NeurIPS.

[104]  Simone Severini,et al.  Quantum machine learning: Challenges and Opportunities , 2019 .

[105]  Iordanis Kerenidis,et al.  q-means: A quantum algorithm for unsupervised machine learning , 2018, NeurIPS.

[106]  Emilie Dufresne,et al.  Sampling Real Algebraic Varieties for Topological Data Analysis , 2018, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA).

[107]  Guang-Can Guo,et al.  Experimental Simultaneous Learning of Multiple Nonclassical Correlations. , 2018, Physical review letters.

[108]  Boris Hanin,et al.  Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations , 2017, Mathematics.

[109]  Mikhail Belkin,et al.  Reconciling modern machine-learning practice and the classical bias–variance trade-off , 2018, Proceedings of the National Academy of Sciences.

[110]  Roger G. Melko,et al.  QuCumber: wavefunction reconstruction with neural networks , 2018, SciPost Physics.

[111]  J. Voight.  Discriminants , 2021, Graduate Texts in Mathematics.