I am a Ph.D. student in the Department of Computer & Information Sciences at University of Delaware, where I work with Prof. Ilya Safro in the Algorithms, AI & Computational Science Lab.

My current research focus involves Machine Learning for Quantum Computing. Before working on ML for QC, I focused on Safety-aware and Robust AI modeling. (I just switched to ML for QC in Jan 2025, so bear with me on the long journey ahead!)

I obtained my B.S. at Texas Christian University.

News

• [Dec 2024]
  • Two papers accepted to AAAI’25
• [Sep 2024]
  • Paper accepted to NeurIPS’24
• [Jul 2024]
  • Participated in UD ATOM Hackathon
  • Paper accepted to CIKM’24
• [Jul 2023]
  • Participated in UD DS + AI Hackathon
  • Paper accepted to CVIU’23, Volume 235

What I’m Working On

My current research focuses on developing machine learning techniques to improve the quantum computing stack, particularly in parameter transferability in the Quantum Approximate Optimization Algorithm (QAOA). This direction sits at the intersection of quantum computing and machine learning, with the goal of making quantum algorithms more generalizable across diverse problem instances. A key challenge in scaling QAOA lies in finding good variational parameters, especially for large problem instances where quantum resources are limited. My goal is to build machine learning models that can learn transferable patterns from small problem instances and generalize them to significantly larger ones, effectively minimizing expensive optimization and circuit evaluations. This approach has the potential to accelerate quantum algorithm deployment in domains like logistics, finance, and network design, where NP-hard problems such as Maximum Cut frequently arise. Furthermore, current quantum hardware remains noisy and limited in qubit count, making it critical to design approaches that optimize performance under these limitations.

TLDR; I aim to bridge machine learning with quantum algorithm design to make quantum optimization more scalable, robust, and ultimately impactful for real-world applications.

Selected Publications

Quantum Era

• Cross-Problem Parameter Transferability in Quantum Approximate Optimization Algorithm: A Machine Learning Approach. Kien X. Nguyen, Bao Bach, and Ilya Safro. Preprint.

Pre-Quantum Era

• Interpretable Failure Detection with Human-Level Concepts. Kien X. Nguyen, Tang Li, and Xi Peng. In Proceedings of the AAAI Conference on Artificial Intelligence, 2025 (Oral).

• Adaptive Cascading Network for Continual Test-time Adaptation. Kien X. Nguyen, Fengchun Qiao, and Xi Peng. In the 33rd ACM International Conference on Information and Knowledge Management, 2024.