Minhui Huang

Research Scientist AI Research for Monetization Meta Inc. (mhhuang@meta.com)

Education

• B.S. in Applied Physics, University of Science and Technology of China, 2013 - 2017.

• Ph.D. in Electrical and Computer Engineering, University of California, Davis, 2017 - 2022.

  • Advisors: Shiqian Ma, Lifeng Lai

Research Interests

• Nonconvex Optimization

• Computational Optimal Transport

• Minimax Problems and Game Theory

• Bilevel Optimization

• Recommendation Systems

Publications

Preprints

• Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis, 2024.

  • Yifan Yang, Hao Ban, Minhui Huang, Shiqian Ma, and Kaiyi Ji

• Hierarchical Structured Neural Network for Retrieval, 2024.

  • Kaushik Rangadurai, Siyang Yuan, Minhui Huang, Yiqun Liu, Golnaz Ghasemiesfeh, Yunchen Pu, Xinfeng Xie, Xingfeng He, Fangzhou Xu, Andrew Cui, Vidhoon Viswanathan, Yan Dong, Liang Xiong, Lin Yang, Liang Wang, Jiyan Yang, Chonglin Sun

• Efficiently Escaping Saddle Points in Bilevel Optimization, 2022.

  • Minhui Huang, Kaiyi Ji, Shiqian Ma, Lifeng Lai

• Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms, 2020.

  • Minhui Huang

Journal Publications

• On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport, Journal of Machine Learning Research (JMLR), 2024.

  • Minhui Huang, Shiqian Ma, Lifeng Lai

• Decentralized Bilevel Optimization, Optimization Letters, 2024.

  • Xuxing Chen, Minhui Huang, Shiqian Ma

• Robust Low-rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method, IEEE Transactions on Signal Processing, 2021.

  • Minhui Huang, Shiqian Ma, Lifeng Lai

Conference Proceedings

• Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization, International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.

  • Wei Shen, Minhui Huang, Jiawei Zhang, Cong Shen

• Achieving Linear Speedup in Non-IID Federated Bilevel Learning, International Conference on Machine Learning (ICML), 2023.

  • Minhui Huang, Dewei Zhang, Kaiyi Ji (the first two authors make equal contribution)

• Decentralized Bilevel Optimization with Improved Complexity, International Conference on Machine Learning (ICML), 2023.

  • Xuxing Chen, Minhui Huang, Shiqian Ma, Krishnakumar Balasubramanian

• A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance, International Conference on Machine Learning (ICML), 2021.

  • Minhui Huang, Shiqian Ma, Lifeng Lai

• Projection Robust Wasserstein Barycenters, International Conference on Machine Learning (ICML), 2021.

  • Minhui Huang, Shiqian Ma, Lifeng Lai

Professional Services

• Reviewer for Journals:

  • Neural Computing

  • Journal of Scientific Computing

  • IEEE Transactions on Information Theory

• Reviewer for Conferences:

  • International Conference on Machine Learning (ICML)

  • Conference on Neural Information Processing Systems (NeurIPS)