Generative Quantum Learning of Joint Probability Distribution Functions
ORAL
Abstract
Modeling joint probability distributions is an important task in a wide variety of fields. One popular technique for this employs a family of multivariate distributions with uniform marginals called copulas. While the theory of modeling joint distributions via copulas is well understood, it gets practically challenging to accurately model real data with many variables. In this work, we design quantum machine learning algorithms to model copulas. We show that any copula can be naturally mapped to a multipartite maximally entangled state. A variational ansatz we christen as a `qopula' creates arbitrary correlations between variables while maintaining the copula structure starting from a set of Bell pairs for two variables, or GHZ states for multiple variables. As an application, we train a Quantum Generative Adversarial Network (QGAN) and a Quantum Circuit Born Machine (QCBM) using this variational ansatz to generate samples from joint distributions of two variables for historical data from the stock market. We demonstrate our generative learning algorithms on trapped ion quantum computers from IonQ for up to 8 qubits and show that our results outperform those obtained through equivalent classical generative learning. Further, we present theoretical arguments for exponential advantage in our model's expressivity over classical models based on communication and computational complexity arguments.
–
Publication: arXiv:2109.06315
Presenters
-
Sonika Johri
IonQ, Inc
Authors
-
Sonika Johri
IonQ, Inc
-
Elton Zhu
Fidelity Center of Applied Technology, FMR LLC
-
Dave Bacon
IonQ Inc
-
Mert Esencan
Fidelity Center of Applied Technology, FMR LLC
-
Jungsang Kim
IonQ Inc
-
Mark Muir
Fidelity Center of Applied Technology, FMR LLC
-
Nikhil Murgai
Fidelity Center of Applied Technology, FMR LLC
-
Jason Nguyen
IonQ Inc
-
Neal Pisenti
IonQ Inc
-
Adam Schouela
Fidelity Center of Applied Technology, FMR LLC
-
Ksenia Sosnova
IonQ Inc
-
Ken Wright
IonQ Inc