Information scrambling and the learning landscape of a quantum machine learning
- CQuIC Seminars
April 23, 2026 3:30 PM -
April 23, 2026 4:30 PM
PAIS 2540
- Host:
- Ivan Deutsch
- Presenter:
- Sabre Kais
Abstract: In this talk, I will focus on quantum machine learning, particularly the Restricted Boltzmann Machine (RBM), as it emerged to be a promising alternative approach to electronic structure calculations of quantum materials leveraging the power of quantum computers. Then, I will introduce and analytically illustrate that the imaginary components of out-of-time order correlators can provide unprecedented insight into the information scrambling capacity of a graph neural network. Furthermore, I will demonstrate that it can be related to conventional measures of correlation like quantum mutual information and rigorously establish the inherent mathematical bounds jointly shared by such seemingly disparate quantities. Such an analysis demystifies the training of quantum machine learning models by unraveling how quantum information is scrambled through such a network introducing correlation surreptitiously among its constituent subsystems and open a window into the underlying physical mechanism behind the emulative ability of the model.
Zoom password availible upon request, email nlordi AT unm.edu
