• Open Access

Quantum mean embedding of probability distributions

Jonas M. Kübler, Krikamol Muandet, and Bernhard Schölkopf
Phys. Rev. Research 1, 033159 – Published 9 December 2019

Abstract

The kernel mean embedding of probability distributions is commonly used in machine learning as an injective mapping from distributions to functions in an infinite-dimensional Hilbert space. It allows us, for example, to define a distance measure between probability distributions, called the maximum mean discrepancy. In this work, we propose to represent probability distributions in a pure quantum state of a system that is described by an infinite-dimensional Hilbert space and prove that the representation is unique if the corresponding kernel function is c0 universal. This enables us to work with an explicit representation of the mean embedding, whereas classically one can only work implicitly with an infinite-dimensional Hilbert space through the use of the kernel trick. We show how this explicit representation can speed up methods that rely on inner products of mean embeddings and discuss the theoretical and experimental challenges that need to be solved in order to achieve these speedups.

  • Figure
  • Figure
  • Received 15 June 2019

DOI:https://doi.org/10.1103/PhysRevResearch.1.033159

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Physics Subject Headings (PhySH)

Quantum Information, Science & Technology

Authors & Affiliations

Jonas M. Kübler*, Krikamol Muandet, and Bernhard Schölkopf

  • Max Planck Institute for Intelligent Systems, 72076 Tübingen, Germany

  • *jmkuebler@tuebingen.mpg.de
  • krikamol@tuebingen.mpg.de
  • bs@tuebingen.mpg.de

Article Text

Click to Expand

References

Click to Expand
Issue

Vol. 1, Iss. 3 — December - December 2019

Subject Areas
Reuse & Permissions

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

×

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×