Lingxiao Qu

Research focus

• Discriminant analysis and kernel methods

Learning discriminative representations, and using kernel methods to handle data that are not linearly separable.

• Small-sample theory

Classification of high-dimensional, small-sample data, including robustness to noise and outliers and class-imbalanced data, with applications to medical, industrial, face and remote sensing data.

• Foundation model embeddings

Discriminant analysis for few-shot text classification on frozen LLM embeddings, including the exact structure of small-sample estimators under balanced k-shot sampling and comparison with trained baselines.

Publications

[1] L. Qu and Y. Pei, "Kernelized Linear Principal Component Discriminant Analysis," Neural Networks, vol. 198, art. 108539, 2026. [DOI]

[2] L. Qu, "Exact Degeneracy Under Balanced k-Shot Sampling: Consequences for Small-Sample Discriminant Analysis on LLM Embeddings," arXiv preprint arXiv:2609.09860, 2026. [arXiv]

[3] L. Qu and Y. Pei, "A Kernel-Based Modular Discriminant Analysis Framework for Small-Sample Learning," under review at Pattern Recognition, 2026. [arXiv]

[4] L. Qu and Y. Pei, "A Comprehensive Review on Discriminant Analysis for Addressing Challenges of Class-Level Limitations, Small Sample Size, and Robustness," Processes, vol. 12, no. 7, art. 1382, 2024. [DOI]

[5] L. Qu, Y. Pei and J. Li, "A Data Analysis Method Using Orthogonal Transformation in a Reproducing Kernel Hilbert Space," in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics (SMC), pp. 887-892, 2023. [DOI]

[6] J. Jiang, L. Zhou and L. Qu, "Coded Distributed Computing Schemes via Grouping Method," in Proc. Int. Conf. Computing and Artificial Intelligence (ICCAI), pp. 98-103, 2022. [DOI]

[7] L. Qu and Y. Pei, "Linear Principal Component Discriminant Analysis via Kernel Methods" (in Japanese), SICE Tohoku Branch Conference, University of Aizu, Japan, 2022.

[8] J. Jiang, Y. Zhong and L. Qu, "An Approach to Improve Distributed Computing," in Proc. Int. Conf. Electronics, Communications and Information Technology (CECIT), pp. 196-205, 2021. [DOI]

[9] J. Jiang and L. Qu, "Cascaded Coded Distributed Computing Schemes Based on Placement Delivery Arrays," IEEE Access, vol. 8, pp. 221385-221395, 2020. [DOI]

Talks

1. Discriminant Analysis for Small-Sample and Robust Learning. 3rd University of Aizu Postgraduate Forum, October 2024.

2. Data Analysis Methods Based on Orthogonal Transformation. IEEE Academia-Industry Summer School, Melbourne (online), 2023.

Teaching

Teaching assistant at the University of Aizu from 2022 to 2025 for Artificial Intelligence, Algorithms and Data Structures, Applied Algebra, Discrete Mathematics and Java Programming. Course instructor for the Venture-Based Project Workshop at the University of Aizu (December 2024 to February 2025), responsible for course design, instruction and student project supervision.

Contact

I am on the academic job market for postdoctoral, assistant professor, research fellow and other academic positions. I welcome correspondence from groups working on statistical machine learning, discriminant data analysis, kernel methods, few-shot learning with foundation models, and related areas, and I would also be glad to collaborate on new directions.

Email: lxqu1110@outlook.com

CV: PDF

Google Scholar: Link

Last updated October 2026