Tianqu Kang

Ph.D. Student, Electrical and Computer Engineering, The University of Texas at Austin

prof_pic.jpg

I am a Ph.D. student in Electrical and Computer Engineering at The University of Texas at Austin, advised by Prof. Gustavo de Veciana. My research interests lie in optimization, theoretical analysis, uncertainty quantification, and networked system design.

My current work focuses on cascaded conformal prediction: producing prediction sets with reliable coverage guarantees while keeping computational cost low. I am developing a two-stage framework that improves the tradeoff between computation and prediction-set size, together with a theoretical analysis of its performance.

Before UT Austin, I received my MPhil in Electronic and Computer Engineering from HKUST in 2025, advised by Prof. Khaled B. Letaief, where I worked on privacy-preserving distributed optimization and federated learning over wireless networks. I received my BEng in Electronic Engineering & Mathematics from HKUST in 2023 with First Class Honors, and spent a research semester at EPFL in 2022.

Selected Publications

  1. MeditCom
    Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks
    Tianqu Kang, Zixin Wang, Hengtao He, and 3 more authors
    In Proc. IEEE Int. Mediterranean Conf. Commun. Netw. (MeditCom), 2025
    DOI arXiv Bib PDF
  2. MeditCom
    The Effect of Quantization in Federated Learning: A Rényi Differential Privacy Perspective
    Tianqu Kang, Lumin Liu, Hengtao He, and 3 more authors
    In Proc. IEEE Int. Mediterranean Conf. Commun. Netw. (MeditCom), 2024
    DOI arXiv Bib PDF