Robust data encodings for quantum classifiers

Data representation is crucial for the success of machine learning models. In the context of quantum machine learning with near-term quantum computers, equally important considerations of how to efficiently input (encode) data and effectively deal with noise arise. In this work, we study data encodings for binary quantum classification and investigate their properties both with and without noise. For the common classifier we consider, we show that encodings determine the classes of learnable decision boundaries as well as the set of points which retain the same classification in the presence of noise. After defining the notion of a robust data encoding, we prove several results on robustness for different channels, discuss the existence of robust encodings, and prove an upper bound on the number of robust points in terms of fidelities between noisy and noiseless states. Numerical results for several example implementations are provided to reinforce our findings.

[1]  G. Vidal,et al.  Universal quantum circuit for two-qubit transformations with three controlled-NOT gates , 2003, quant-ph/0307177.

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  E. Solano,et al.  Quantum-classical computation of Schwinger model dynamics using quantum computers , 2018, Physical Review A.

[4]  Iordanis Kerenidis,et al.  Quantum classification of the MNIST dataset via Slow Feature Analysis , 2018, ArXiv.

[5]  P. Coveney,et al.  Scalable Quantum Simulation of Molecular Energies , 2015, 1512.06860.

[6]  D. Angluin,et al.  Learning From Noisy Examples , 1988, Machine Learning.

[7]  Simone Severini,et al.  Quantum linear systems algorithms: a primer , 2018, ArXiv.

[8]  Craig Gidney,et al.  How to factor 2048 bit RSA integers in 8 hours using 20 million noisy qubits , 2019, Quantum.

[9]  Stuart Hadfield,et al.  Characterizing local noise in QAOA circuits , 2020, IOP SciNotes.

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

[11]  J. Biamonte.  Universal variational quantum computation , 2019, Physical Review A.

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

[13]  Michael Broughton,et al.  A quantum algorithm to train neural networks using low-depth circuits , 2017, 1712.05304.

[14]  M. Schuld,et al.  Circuit-centric quantum classifiers , 2018, Physical Review A.

[15]  David J. Schwab,et al.  Supervised Learning with Tensor Networks , 2016, NIPS.

[16]  Natalie Klco,et al.  Digitization of scalar fields for quantum computing , 2018, Physical Review A.

[17]  Xiao Yuan,et al.  Variational algorithms for linear algebra , 2019, Science Bulletin.

[18]  Iordanis Kerenidis,et al.  Quantum Recommendation Systems , 2016, ITCS.

[19]  Ryan LaRose,et al.  Variational Quantum Linear Solver: A Hybrid Algorithm for Linear Systems , 2019, 1909.05820.

[20]  Daniel A. Lidar.  Review of Decoherence‐Free Subspaces, Noiseless Subsystems, and Dynamical Decoupling , 2014 .

[21]  J. Schauder,et al.  Der Fixpunktsatz in Funktionalraümen , 1930 .

[22]  Serdar Kuyucak,et al.  Comment on “ Δ I = 4 Bifurcation in Ground Bands of Even-Even Nuclei and the Interacting Boson Model” , 1999 .

[23]  Dacheng Tao,et al.  The Expressive Power of Parameterized Quantum Circuits , 2018, ArXiv.

[24]  Lei Wang,et al.  Differentiable Learning of Quantum Circuit Born Machine , 2018, Physical Review A.

[25]  Alán Aspuru-Guzik,et al.  A variational eigenvalue solver on a photonic quantum processor , 2013, Nature Communications.

[26]  Sirui Lu,et al.  Quantum Adversarial Machine Learning , 2020, ArXiv.

[27]  L. Banchi,et al.  Noise-resilient variational hybrid quantum-classical optimization , 2019, Physical Review A.

[28]  Alán Aspuru-Guzik,et al.  The theory of variational hybrid quantum-classical algorithms , 2015, 1509.04279.

[29]  Kristan Temme,et al.  Error Mitigation for Short-Depth Quantum Circuits. , 2016, Physical review letters.

[30]  Elham Kashefi,et al.  The Born supremacy: quantum advantage and training of an Ising Born machine , 2019, npj Quantum Information.

[31]  Soonwon Choi,et al.  Quantum convolutional neural networks , 2018, Nature Physics.

[32]  John Watrous,et al.  The Theory of Quantum Information , 2018 .

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

[34]  Ryan Babbush,et al.  The theory of variational hybrid quantum-classical algorithms , 2015, 1509.04279.

[35]  M. Benedetti,et al.  Quantum circuit structure learning , 2019, 1905.09692.

[36]  Aram W. Harrow,et al.  Quantum algorithm for solving linear systems of equations , 2010 .

[37]  Peter W. Shor,et al.  Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer , 1995, SIAM Rev..

[38]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[39]  Rocco A. Servedio,et al.  Equivalences and Separations Between Quantum and Classical Learnability , 2004, SIAM J. Comput..

[40]  Patrick J. Coles,et al.  Variational consistent histories as a hybrid algorithm for quantum foundations , 2018, Nature Communications.

[41]  Logan G. Wright,et al.  The Capacity of Quantum Neural Networks , 2019, 2020 Conference on Lasers and Electro-Optics (CLEO).

[42]  Bernhard Schölkopf,et al.  Quantum Mean Embedding of Probability Distributions , 2019, Physical Review Research.

[43]  Edward Grant,et al.  Cost function embedding and dataset encoding for machine learning with parameterized quantum circuits , 2019 .

[44]  Naoki Yamamoto,et al.  Analysis and synthesis of feature map for kernel-based quantum classifier , 2020, Quantum Mach. Intell..

[45]  J. Gambetta,et al.  Tapering off qubits to simulate fermionic Hamiltonians , 2017, 1701.08213.

[46]  Ryan LaRose,et al.  Overview and Comparison of Gate Level Quantum Software Platforms , 2018, Quantum.

[47]  Ryan Babbush,et al.  Decoding quantum errors with subspace expansions , 2019, Nature Communications.

[48]  Seth Lloyd,et al.  Quantum embeddings for machine learning , 2020 .

[49]  Francesco Petruccione,et al.  Quantum classifier with tailored quantum kernel , 2019 .

[50]  Alejandro Perdomo-Ortiz,et al.  A generative modeling approach for benchmarking and training shallow quantum circuits , 2018, npj Quantum Information.

[51]  Maxwell Henderson,et al.  Quanvolutional neural networks: powering image recognition with quantum circuits , 2019, Quantum Machine Intelligence.

[52]  Ryan LaRose,et al.  Quantum-assisted quantum compiling , 2018, Quantum.

[53]  Mahabubul Alam,et al.  Analysis of Quantum Approximate Optimization Algorithm under Realistic Noise in Superconducting Qubits , 2019, ArXiv.

[54]  Maria Schuld,et al.  Quantum ensembles of quantum classifiers , 2017, Scientific Reports.

[55]  Hsin-Yuan Huang,et al.  Near-term quantum algorithms for linear systems of equations , 2019, ArXiv.

[56]  E. Knill,et al.  A scheme for efficient quantum computation with linear optics , 2001, Nature.

[57]  Patrick J. Coles,et al.  Variational quantum state diagonalization , 2018, npj Quantum Information.

[58]  A. Harrow,et al.  Quantum algorithm for linear systems of equations. , 2008, Physical review letters.

[59]  Akira Sone,et al.  Cost-Function-Dependent Barren Plateaus in Shallow Quantum Neural Networks , 2020, ArXiv.

[60]  Simone Severini,et al.  Hierarchical quantum classifiers , 2018, npj Quantum Information.

[61]  Spiros Kechrimparis,et al.  Channel Coding of a Quantum Measurement , 2019, IEEE Journal on Selected Areas in Communications.

[62]  Maria Schuld,et al.  Quantum Machine Learning in Feature Hilbert Spaces. , 2018, Physical review letters.

[63]  Tyson Jones,et al.  QuEST and High Performance Simulation of Quantum Computers , 2018, Scientific Reports.

[64]  E. Farhi,et al.  A Quantum Approximate Optimization Algorithm , 2014, 1411.4028.

[65]  Cheng Xue,et al.  Effects of Quantum Noise on Quantum Approximate Optimization Algorithm , 2019 .

[66]  Peter Wittek,et al.  Quantum Machine Learning: What Quantum Computing Means to Data Mining , 2014 .

[67]  David P. DiVincenzo,et al.  Quantum information and computation , 2000, Nature.

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

[69]  Marcello Benedetti,et al.  Parameterized quantum circuits as machine learning models , 2019, Quantum Science and Technology.

[70]  Kunal Sharma,et al.  Noise resilience of variational quantum compiling , 2019, New Journal of Physics.

[71]  Jos'e I. Latorre,et al.  Data re-uploading for a universal quantum classifier , 2019, Quantum.

[72]  Jack K. Fitzsimons,et al.  Smooth input preparation for quantum and quantum-inspired machine learning , 2018, Quantum Machine Intelligence.

[73]  Kristan Temme,et al.  Supervised learning with quantum-enhanced feature spaces , 2018, Nature.

[74]  R. Feynman.  Simulating physics with computers , 1999 .

[75]  Nathan Killoran,et al.  Transfer learning in hybrid classical-quantum neural networks , 2019, Quantum.

[76]  Jeroen van de Graaf,et al.  Cryptographic Distinguishability Measures for Quantum-Mechanical States , 1997, IEEE Trans. Inf. Theory.

[77]  Ronald de Wolf,et al.  Optimal Quantum Sample Complexity of Learning Algorithms , 2016, CCC.

[78]  John Preskill,et al.  Quantum Computing in the NISQ era and beyond , 2018, Quantum.

[79]  Ryan Babbush,et al.  Barren plateaus in quantum neural network training landscapes , 2018, Nature Communications.

[80]  Srinivasan Arunachalam,et al.  Quantum statistical query learning , 2020, ArXiv.

[81]  Peter J. Love,et al.  A variational eigenvalue solver on a quantum processor , 2018 .

[82]  Daniel A. Lidar,et al.  Decoherence-Free Subspaces for Quantum Computation , 1998, quant-ph/9807004.

[83]  Edward Grant,et al.  An initialization strategy for addressing barren plateaus in parametrized quantum circuits , 2019, Quantum.

[84]  Travis S. Humble,et al.  Quantum supremacy using a programmable superconducting processor , 2019, Nature.

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

[86]  E. Knill,et al.  DYNAMICAL DECOUPLING OF OPEN QUANTUM SYSTEMS , 1998, quant-ph/9809071.