He received his bachelor's degree in 2017 from the Department of Mathematics at Zhejiang University. He started his Master's study in September 2017 in Academy of Mathematics and Systems Science of Chinese Academy of Sciences, under the supervision of Professor Xin Liu. He then became a PhD candidate there in August 2019.  After that, he visited PolyU for two years, sponsored by Xiaojun Chen. He got the Ph.D. degree in June 2022. He was a Postdoctoral Research Associate at the Rensselaer Polytechnic Institute from 2022 to 2025, sponsored by Yangyang Xu. He then joined the AMA, Hong Kong Polytechnic University as a Research Assistant Professor.

• First-order methods for large-scale nonconvex (nonsmooth) optimization 

• Stochastic (sub)gradient methods for statistical and machine learning

• Computation complexity analysis

• Applications, e.g., fairness-constrained problems, deep neural networks, distributed robust optimization, decentralized distributed learning, semi-supervised learning, bilevel optimization, minimax problems, LLM

• Wei Liu, Xin Liu, and Xiaojun Chen, Linearly-constrained nonsmooth optimization for training autoencoders. SIAM Journal on Optimization. 2022. ARXIV Code SIOPT

• Wei Liu, Xin Liu, and Xiaojun Chen, An inexact augmented Lagrangian algorithm for training leaky ReLU neural network with group sparsity. Journal of Machine Learning Research. 2023. ARXIV Code JMLR

• Wei Liu, Qihang Lin, Yangyang Xu, First-order methods for affinely constrained composite non-convex non-smooth problems: Lower complexity bound and near-optimal methods. Mathematics of Operations Research. ARXIV MOR.

• Wei Liu, Yangyang Xu, A single-loop SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization. ARXIV

• Wei Liu, Muhammad Khan, Gabriel Mancino-Ball, Yangyang Xu, A stochastic smoothing framework for nonconvex-nonconcave min-sum-max problems with applications to Wasserstein distributionally robust optimization.  ARXIV