The quantum Wasserstein distance of order 1

We propose a generalization of the Wasserstein distance of order 1 to the quantum states of $n$ qudits. The proposal recovers the Hamming distance for the vectors of the canonical basis, and more generally the classical Wasserstein distance for quantum states diagonal in the canonical basis. The proposed distance is invariant with respect to permutations of the qudits and unitary operations acting on one qudit and is additive with respect to the tensor product. Our main result is a continuity bound for the von Neumann entropy with respect to the proposed distance, which significantly strengthens the best continuity bound with respect to the trace distance. We also propose a generalization of the Lipschitz constant to quantum observables. The notion of quantum Lipschitz constant allows us to compute the proposed distance with a semidefinite program. We prove a quantum version of Marton's transportation inequality and a quantum Gaussian concentration inequality for the spectrum of quantum Lipschitz observables. Moreover, we derive bounds on the contraction coefficients of shallow quantum circuits and of the tensor product of one-qudit quantum channels with respect to the proposed distance. We discuss other possible applications in quantum machine learning, quantum Shannon theory, and quantum many-body systems.

[1]  Sina Salek,et al.  Quantum Rate-Distortion Coding of Relevant Information , 2017, IEEE Transactions on Information Theory.

[2]  Mark M. Wilde,et al.  Quantum Rate-Distortion Coding With Auxiliary Resources , 2012, IEEE Transactions on Information Theory.

[3]  D. Ornstein An Application of Ergodic Theory to Probability Theory , 1973 .

[4]  K. Marton Bounding $\bar{d}$-distance by informational divergence: a method to prove measure concentration , 1996 .

[5]  A. Tannenbaum,et al.  Wasserstein Geometry of Quantum States and Optimal Transport of Matrix-Valued Measures , 2018 .

[6]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[7]  Seth Lloyd,et al.  Quantum Generative Adversarial Learning. , 2018, Physical review letters.

[8]  N. Datta,et al.  Relating Relative Entropy, Optimal Transport and Fisher Information: A Quantum HWI Inequality , 2017, Annales Henri Poincaré.

[9]  A. Winter,et al.  Distillation of secret key and entanglement from quantum states , 2003, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[10]  F. Fagnola,et al.  On quantum versions of the classical Wasserstein distance , 2017 .

[11]  E. Carlen,et al.  An Analog of the 2-Wasserstein Metric in Non-Commutative Probability Under Which the Fermionic Fokker–Planck Equation is Gradient Flow for the Entropy , 2012, 1203.5377.

[12]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[13]  Yihong Wu,et al.  Wasserstein Continuity of Entropy and Outer Bounds for Interference Channels , 2015, IEEE Transactions on Information Theory.

[14]  Toby Berger,et al.  Quantum rate-distortion theory for memoryless sources , 2002, IEEE Trans. Inf. Theory.

[15]  Alexander Semenovich Holevo,et al.  Quantum Systems, Channels, Information: A Mathematical Introduction , 2019 .

[16]  Wuchen Li,et al.  Quantum Statistical Learning via Quantum Wasserstein Natural Gradient , 2020, ArXiv.

[17]  Emanuele Caglioti,et al.  Quantum Optimal Transport is Cheaper , 2019, ArXiv.

[18]  M. Junge,et al.  Noncommutative martingale deviation and Poincaré type inequalities with applications , 2012, 1211.3209.

[19]  R. Gray Entropy and Information Theory , 1990, Springer New York.

[20]  N. Datta,et al.  Concentration of quantum states from quantum functional and transportation cost inequalities , 2017, Journal of Mathematical Physics.

[21]  Thomas Vidick,et al.  A simple proof of Renner's exponential de Finetti theorem , 2016, 1608.04814.

[22]  D. Voiculescu,et al.  A free probability analogue of the Wasserstein metric on the trace-state space , 2000, math/0006044.

[23]  Shouvanik Chakrabarti,et al.  Quantum Wasserstein Generative Adversarial Networks , 2019, NeurIPS.

[24]  Connes distance and optimal transport , 2018, 1803.07538.

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

[26]  L. Kantorovich On the Translocation of Masses , 2006 .

[27]  Howard Barnum Quantum rate-distortion coding , 1998 .

[28]  M. Talagrand A new look at independence , 1996 .

[29]  A. Vershik Long History of the Monge-Kantorovich Transportation Problem , 2013 .

[30]  C. Villani Optimal Transport: Old and New , 2008 .

[31]  Xiao-Yu Chen,et al.  Entanglement Information Rate Distortion of a Quantum Gaussian Source , 2008, IEEE Transactions on Information Theory.

[32]  Igal Sason,et al.  Concentration of Measure Inequalities in Information Theory, Communications, and Coding , 2012, Found. Trends Commun. Inf. Theory.

[33]  L. Ambrosio,et al.  Gradient Flows: In Metric Spaces and in the Space of Probability Measures , 2005 .

[34]  M. Talagrand Transportation cost for Gaussian and other product measures , 1996 .

[35]  Robert Koenig,et al.  Obstacles to Variational Quantum Optimization from Symmetry Protection. , 2019, Physical review letters.

[36]  Wojciech Słomczyński,et al.  The Monge metric on the sphere and geometry of quantum states , 2000, quant-ph/0008016.

[37]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[38]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[39]  Marco Cuturi,et al.  Computational Optimal Transport: With Applications to Data Science , 2019 .

[40]  Wojciech Słomczyński,et al.  The Monge distance between quantum states , 1997, quant-ph/9711011.

[41]  Julián Agredo,et al.  A Wasserstein-type Distance to Measure Deviation from Equilibrium of Quantum Markov Semigroups , 2013, Open Syst. Inf. Dyn..

[42]  E. Carlen,et al.  Gradient flow and entropy inequalities for quantum Markov semigroups with detailed balance , 2016, 1609.01254.

[43]  Christian L'eonard,et al.  Transport Inequalities. A Survey , 2010, 1003.3852.

[44]  Thierry Paul,et al.  The Schrödinger Equation in the Mean-Field and Semiclassical Regime , 2015, 1510.06681.

[45]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[46]  T. Paul,et al.  Towards optimal transport for quantum densities , 2021, ANNALI SCUOLA NORMALE SUPERIORE - CLASSE DI SCIENZE.

[47]  Yoshihiko Hasegawa,et al.  Geometrical Bounds of the Irreversibility in Markovian Systems. , 2020, Physical review letters.

[48]  Tryphon T. Georgiou,et al.  Matrix Optimal Mass Transport: A Quantum Mechanical Approach , 2016, IEEE Transactions on Automatic Control.

[49]  T. Paul,et al.  On the Mean Field and Classical Limits of Quantum Mechanics , 2015, Communications in Mathematical Physics.

[50]  Kazuki Ikeda,et al.  Foundation of quantum optimal transport and applications , 2019, Quantum Information Processing.

[51]  R. Schumann Quantum Information Theory , 2000, quant-ph/0010060.

[52]  Lior Eldar,et al.  Local Hamiltonians Whose Ground States Are Hard to Approximate , 2015, 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS).

[53]  P. Wittek,et al.  Vulnerability of quantum classification to adversarial perturbations , 2019, Physical Review A.

[54]  Yann Brenier,et al.  A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem , 2000, Numerische Mathematik.

[55]  F. Golse The quantum N-body problem in the mean-field and semiclassical regime , 2018, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[56]  Michael M. Wolf,et al.  Hilbert's projective metric in quantum information theory , 2011, 1102.5170.

[57]  Ievgeniia Oshurko Quantum Machine Learning , 2020, Quantum Computing.

[58]  Yongxin Chen,et al.  Vector and Matrix Optimal Mass Transport: Theory, Algorithm, and Applications , 2017, SIAM J. Sci. Comput..

[59]  Tryphon T. Georgiou,et al.  Matricial Wasserstein-1 Distance , 2017, IEEE Control Systems Letters.

[60]  Thierry Paul,et al.  WAVE PACKETS AND THE QUADRATIC MONGE-KANTOROVICH DISTANCE IN QUANTUM MECHANICS , 2017, 1707.04161.

[61]  Katalin Marton,et al.  A simple proof of the blowing-up lemma , 1986, IEEE Trans. Inf. Theory.

[62]  Mark M. Wilde,et al.  Quantum Rate Distortion, Reverse Shannon Theorems, and Source-Channel Separation , 2011, IEEE Transactions on Information Theory.

[63]  Giacomo De Palma,et al.  The conditional Entropy Power Inequality for quantum additive noise channels , 2018, Journal of Mathematical Physics.

[64]  Rocco Duvenhage,et al.  Balance Between Quantum Markov Semigroups , 2017, Annales Henri Poincaré.

[66]  K. Temme,et al.  Quantum logarithmic Sobolev inequalities and rapid mixing , 2012, 1207.3261.

[67]  Mark M. Wilde,et al.  Quantum-to-classical rate distortion coding , 2012, ArXiv.

[68]  A. Connes,et al.  THE METRIC ASPECT OF NONCOMMUTATIVE GEOMETRY , 1992 .

[69]  E. Carlen,et al.  Non-commutative Calculus, Optimal Transport and Functional Inequalities in Dissipative Quantum Systems , 2018, Journal of statistical physics.

[70]  J. Agredo ON EXPONENTIAL CONVERGENCE OF GENERIC QUANTUM MARKOV SEMIGROUPS IN A WASSERSTEIN-TYPE DISTANCE , 2016 .

[71]  Igor Devetak,et al.  Quantum rate-distortion theory for i.i.d. sources , 2000, Proceedings. 2001 IEEE International Symposium on Information Theory (IEEE Cat. No.01CH37252).

[72]  Scott Aaronson,et al.  The learnability of quantum states , 2006, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[73]  Gabriel Peyré,et al.  Learning Generative Models with Sinkhorn Divergences , 2017, AISTATS.

[74]  J. Borwein,et al.  Convex Analysis And Nonlinear Optimization , 2000 .

[75]  Guy N. Rothblum,et al.  Gentle measurement of quantum states and differential privacy , 2019, Electron. Colloquium Comput. Complex..

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