Quantum Lunch Series Event – Speaker Milad Marvian

Talk Title: Quantum Earth Mover’s Distance: A New Approach to Learning Quantum Data

Speaker: Professor Milad Marvian, University of New Mexico

Milad Marvian is an Assistant Professor in the Department of Electrical & Computer Engineering at the University of New Mexico and also a member of the Center for Quantum Information and Control (CQuIC). He completed his Ph.D. in 2018 at the University of Southern California and before joining UNM was a postdoctoral associate at MIT. His research interest includes quantum algorithms and quantum machine learning, quantum error correction, and open quantum systems.

Abstract:
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.

This is a Virtual Event.

For more information email:

quantumcomputing@ncsu.edu