Welcome to my homepage!
My name is Zhuqing (Zuki) Liu. I am a fifth-year Ph.D. student in the Dept. of ECE at The Ohio State University, supervised by Prof. Jia(Kevin) Liu.
Email: liu.9384@osu.edu
Google Scholar: https://scholar.google.com/citations?user=JwF6ajgAAAAJ&hl=en
Linkedin: https://www.linkedin.com/in/zhuqing-liu-816610155/
RELATED SKILLS
Optimization: Mathematics and statistics, data analysis, model selection and evaluation and theoretical knowledge.
Operation Research: Mathematical modeling, algorithm development, and simulations.
Programming languages: Python (Keras, Tensorflow, Pytorch, Numpy, Pandas), SQL, MATLAB, C#, and C/C++.
Platforms: AWS, Google Cloud, CUDA, MySQL, and Linux.
RESEARCH INTERESTS
First-order stochastic optimization for machine learning
Communication efficiency in distributed/federated/decentralized learning
Meta learning, Natural language processing, LLM
Publications
Zhuqing Liu, Xin Zhang, Jia Liu, Zhengyuan Zhu, and Songtao Lu, "PILOT: An O(1/T)-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation," in Proc. ICLR, Vienna, Austria, May. 2024, Spotlight (acceptance rate: 5%).
Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, and Jia Liu, "Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning," in Proc. ICML, Honolulu, HI, Jul. 2023 (acceptance rate: 27.9%).
Zhuqing Liu, Xin Zhang, Songtao Lu, and Jia Liu, "PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities," in Proc. ACM MobiHoc, Washington, DC, Oct. 2023 (acceptance rate: 21.9%).
Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, and Jia Liu, "INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks," in Proc. ACM MobiHoc, Seoul, South Korea, Oct. 2022 (acceptance rate: 19.8%).
Zhuqing Liu, Xin Zhang, and Jia Liu, "SYNTHESIS: A Semi-Asynchronous Path-Integrated Stochastic Gradient Method for Distributed Learning in Computing Clusters," in Proc. ACM MobiHoc, Seoul, South Korea, Oct. 2022 (acceptance rate: 19.8%).
Xin Zhang, Minghong Fang, Zhuqing Liu, Haibo Yang, Jia Liu, and Zhengyuan Zhu, "NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data," in Proc. ACM MobiHoc, Seoul, South Korea, Oct. 2022 (acceptance rate: 19.8%).
Haibo Yang, Zhuqing Liu, Xin Zhang, and Jia Liu, "SAGDA: Achieving O(ε-2) Communication Complexity in Federated Min-Max Learning," in Proc. NeurIPS, New Orleans, LA, Dec. 2022 (acceptance rate: 25.6%).
Zhuqing Liu*, Xin Zhang*, Jia Liu, Zhengyuan Zhu, and Songtao Lu, "Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning," in Proc. NeurIPS, Virtual Event, Dec. 2021 (acceptance rate: 26%).
Peiwen Qiu, Yining Li, Zhuqing Liu, Prashant Khanduri, Jia Liu, Ness B. Shroff, Elizabeth S. Bentley, and Kurt Turck, "DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization," in Proc. IEEE INFOCOM, New York City, NY, May 2023 (acceptance rate: 19.2%).
Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong, and Michinari Momma "Federated Multi-Objective Learning," in Proc. NeurIPS, New Orleans, LA, Dec. 2023 (acceptance rate: 26.1%).
Luning Bi, Fei Tao, Ying Zuo, Zhuqing Liu. “Energy-aware material selection for product with multi-component under cloud environment”, ASME Journal of Computing and Information Science in Engineering, 2017.
Zhuqing Liu, Haibin Duan, Yijun Yang, Xiaoguang Hu. "Pendulum-like Oscillation Controller for UAV Based on Levy-flight Pigeon-inspired Optimization and LQR", IEEE Symposium Series on Computational Intelligence, 2016. (acceptance rate: 33%).
*The authors are joint first authors with equal contributions.
Academical Services
Served as Reviewer for JSAIT 2023, TNSE 2023, INFOCOM 2023, ICML 2022, NeurIPS 2022, AAAI 2022.