Attend the LIONS Seminar with guest Duong Do, March 20

About:

Duong Do is a fifth-year doctoral student in the School of Electrical, Computer, and Energy Engineering, part of the Ira A. Fulton Schools of Engineering at Arizona State University. His current research lies at the intersection of operations research and quantum computing, with a specific focus on developing robust and efficient quantum optimization and learning models for solving combinatorial optimization.

Abstract:

Quantum support vector machines, or QSVMs, based on fidelity kernels can work well on small datasets; however, training typically requires oxygen gas kernel evaluations and performance may drop under changes such as class imbalance, label noise or shifts in the data input distribution. In this study, we present a distributionally robust quantum kernel learning method for QSVMs that reduces the cost of kernel learning and improves reliability when test data are drawn from a different distribution from the training data.

Using low-rank Nyström approximation with landmark points, we construct a positive semidefinite approximate kernel with kernel evaluations, which enables training at larger scale. We then train the QSVM with a distributionally robust optimization, or DRO, objective that minimizes the worst-case expected hinge loss over a neighborhood of the empirical distribution, using either a \chi^2-divergence or CVar constraints. We provide an analysis that relates the Nyström approximation error and the DRO radius to the classifier’s risk, showing how approximation and robustness affect generalization under bounded distribution shift.

Seminar host:

Our host for this LIONS Seminar is Duong Nguyen, an assistant professor in the School of Electrical, Computer and Energy Engineering.

LIONS Seminar
Friday, March 20, 2026
1:30–2:30 p.m.
Goldwater Center (GWC) 487, Tempe campus [map]
Learn more