Biography

Hi, everyone! I am Meiyu Zhong, a Ph.D. student in the Department of Electrical and Computer Engineering, University of Arizona. I am very lucky to work with Dr. Ravi Tandon. Previously, I received my M.S. degree from University of Southern California and B.S. degree in Shanghai University, majoring in Electrical Engineering.

Education

• Department of Electrical and Computer Engineering, University of Arizona, 08/2021-Present
  • Major in Electrical Engineering
  • GPA: 4.0/4.0
  • Research interest: Fairness and Robostness in machine learning
• Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, 08/2019-05/2021
  • Major in Electrical Engineering
  • GPA: 3.77/4.0
• Department of Electrical and Computer Engineering, Shanghai University, 09/2015-06/2019
  • Major in Electrical Engineering
  • Major GPA: 3.77/4.0

Research Interests

• Efficient LLM (Speculative Decoding)
• Fair Machine Learning Algorithms and Fair LLM Design
• Certified Robust Algorithms and Adversarial Training

Work experience

• Smart Manufacture & AI Data Science intern

  Micron Technology

  2024 Feb - present

• Data Science intern

  GiantKONE Elevator Co., Ltd.

  Aug 2018 - Nov 2018

Skills

• Programming language: Python (proficient), Matlab (proficient), C/C++ (familiar), SQL (familiar).
• Tools&Packages: PyTorch, Hugging Face, HPC, Latex, NumPy, Pandas, Scikit-learn, TensorFlow, Git, Unix/Linux, etc.
• Robust machine learning: Certified Robustness, Adversarial Training.
• Fair machine learning: Group Fairness, Individual Fairness.

Papers

• Meiyu Zhong *, Noel Teku *, Ravi Tandon, Speeding up Speculative Decoding via Sequential Approximate Verification, Proceedings of the 3rd Efficient Systems for Foundation Models Workshop at the 41 st International Conference on Machine Learning (ICML), Vancouver, Canada. PMLR 267, 2025.

• Meiyu Zhong, Ravi Tandon, SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing, IEEE Transactions on Information Forensics and Security, 2025 (To be published).

• Wenhan Zhang *, Meiyu Zhong *, Ravi Tandon, Marwan Krunz, Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification. Proc. of the IEEE MILCOM Conference, October. 2024.

• Meiyu Zhong, Ravi Tandon, Learning Fair Robustness via Domain Mixup, 57th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Oct 2024.

• Meiyu Zhong, Ravi Tandon, Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds, IEEE International Symposium on Information Theory (ISIT), Athens, Greece, July 2024.

• Meiyu Zhong, Ravi Tandon, Learning Fair Classifiers via Min-Max F-divergence Regularization, 59th Annual Allerton Conference on Communications, Control and Computing, Monticello, IL, September 2023

• Xingchen Li, Meiyu Zhong, “Hardware Design of Basketball Robot based on Flyback Topology and Verilog HDL”, International Conference on Information Systems and Computer Aided Education (ICISCAE), 2018, Vol 2:508-510.

Awards and Honors

• Champion of the 19th China Basketball Robot Competitoon, Yibin, China, 2018 - 2019
• Academic Excellent Scholarship Level I (top 5), Sep 2018 - Jul 2019
• Hezong Welding Academic Scholarship Level II, Sep 2017 - Jul 2018
• Hezong Welding Academic Scholarship Level III, Sep 2016 - Jul 2017
• Leadership Scholarship, Sep 2015 - Jul 2016