Quantum Data Compression and Quantum Cross Entropy

Quantum machine learning is an emerging field at the intersection of machine learning and quantum computing. A central quantity for the theoretical foundation of quantum machine learning is the quantum cross entropy. In this paper, we present one operational interpretation of this quantity, that the quantum cross entropy is the compression rate for sub-optimal quantum source coding. To do so, we give a simple, universal quantum data compression protocol, which is developed based on quantum generalization of variable-length coding, as well as quantum strong typicality.

[1]  Shangnan Zhou.  Complexity, Entropy, and Markov Chains , 2019, 1902.10538.

[2]  Stefano Facchini,et al.  Quantum Circuits for the Unitary Permutation Problem , 2014, TAMC.

[3]  Zhou Shangnan,et al.  Quantum Cross Entropy and Maximum Likelihood Principle , 2021, ArXiv.

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

[5]  Thomas M. Cover,et al.  Network Information Theory , 2001 .

[6]  C. H. Bennett,et al.  Universal quantum data compression via nondestructive tomography , 2004, quant-ph/0403078.

[7]  Tobias J. Osborne,et al.  Training deep quantum neural networks , 2020, Nature Communications.

[8]  Andris Ambainis,et al.  Understanding Quantum Algorithms via Query Complexity , 2017, Proceedings of the International Congress of Mathematicians (ICM 2018).

[9]  D. Petz,et al.  Stationary quantum source coding , 1999, quant-ph/9912103.

[10]  Richard Jozsa,et al.  Universal quantum information compression and degrees of prior knowledge , 2003, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[11]  B. Valiron,et al.  Quantum computations without definite causal structure , 2009, 0912.0195.

[12]  Schumacher,et al.  Quantum coding. , 1995, Physical review. A, Atomic, molecular, and optical physics.

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

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

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

[16]  Samuel L. Braunstein,et al.  A quantum analog of huffman coding , 2000, IEEE Trans. Inf. Theory.

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

[18]  Michael D. Westmoreland,et al.  Indeterminate-length quantum coding , 2000, quant-ph/0011014.

[19]  John Preskill,et al.  Code properties from holographic geometries , 2016, 1612.00017.

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