6–11 Jun 2021
Underline Conference System
America/Toronto timezone
Welcome to the 2021 CAP Congress Program website! / Bienvenue au siteweb du programme du Congrès de l'ACP 2021!

Quantum Earth Mover's Distance: A New Approach to Learning Quantum Data

8 Jun 2021, 12:00
30m
Underline Conference System

Underline Conference System

Invited Speaker / Conférencier(ère) invité(e) Symposia Day (DTP) - Quantum Machine Learning TS-2 Quantum Machine Learning (DTP) / Apprentissage automatique quantique (DPT)

Speaker

Dr Milad Marvian (University of New Mexico)

Description

In this talk, I will introduce a generalization of the earth mover's distance to the set of quantum states. The proposed distance recovers the Hamming distance for the vectors of the canonical basis, and more generally the classical earth mover's distance for quantum states diagonal in the canonical basis. I will discuss some desirable properties of this distance, including a continuity bound for the von Neumann entropy and its insensitivity to local perturbations, and I will show how these properties make the distance suitable for learning quantum data using quantum generative adversarial networks
Based on https://arxiv.org/abs/2009.04469 and https://arxiv.org/abs/2101.03037.

Primary author

Dr Milad Marvian (University of New Mexico)

Presentation materials

There are no materials yet.