Publications
#: supervised student author, *: equal contribution (alphabetical order)
(New! ) Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis # , Mingrui Liu .Neural Information Processing Systems 37 , 2024. (NeurIPS 2024)
(New! ) An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness # , Jie Hao# , Mingrui Liu .Neural Information Processing Systems 37 , 2024. (NeurIPS 2024)
(New! ) Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective # , Michael Crawshaw# , Mingrui Liu . International Conference on Machine Learning , 2024. (ICML 2024)
(New! ) A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness # , Jie Hao# , Mingrui Liu . International Conference on Machine Learning , 2024. (ICML 2024)
(New! ) Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis # , Xiaochuan Gong# , Mingrui Liu .International Conference on Learning Representations , 2024. (ICLR 2024) (Spotlight, 5% acceptance rate)
Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds # , Yajie Bao# , Mingrui Liu .Neural Information Processing Systems 37 , 2023. (NeurIPS 2023)
Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization # , Amarda Shehu, Mingrui Liu .Neural Information Processing Systems 37 , 2023. (NeurIPS 2023)
Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm # , Kaiyi Ji, Mingrui Liu .Neural Information Processing Systems 37 , 2023. (NeurIPS 2023)
AUC Maximization in Imbalanced Lifelong Learning # , Jie Hao# , Yunhui Guo, Mingrui Liu .Conference on Uncertainty in Artificial Intelligence , 2023. (UAI 2023)
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data # , Yajie Bao# , Mingrui Liu .International Conference on Learning Representations , 2023. (ICLR 2023)
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks Mingrui Liu , Zhenxun Zhuang, Yunwen Lei, Chunyang Liao.Neural Information Processing Systems 36 , 2022. (NeurIPS 2022) (Spotlight, 5% acceptance rate)
Robustness to Unbounded Smoothness of Generalized SignSGD #* , Mingrui Liu* , Francesco Orabona* , Wei Zhang* , Zhenxun Zhuang* .Neural Information Processing Systems 36 , 2022. (NeurIPS 2022)
Will Bilevel Optimizers Benefit from Loops Mingrui Liu , Yingbin Liang, Lei Ying.Neural Information Processing Systems 36 , 2022. (NeurIPS 2022) (Spotlight, 5% acceptance rate)
Fast Composite Optimization and Statistical Recovery in Federated Learning # , Michael Crawshaw# , Shan Luo, Mingrui Liu . International Conference on Machine Learning , 2022. (ICML 2022)
Understanding AdamW through Proximal Methods and Scale-Freeness Mingrui Liu , Ashok Cutkosky, Francesco Orabona.Transactions on Machine Learning Research , 2022. (TMLR 2022)
On the Initialization for Convex-Concave Min-max Problems Mingrui Liu , Francesco Orabona.Algorithmic Learning Theory , 2022. (ALT 2022)
On the Last Iterate Convergence of Momentum Methods Mingrui Liu , Francesco Orabona. Algorithmic Learning Theory , 2022. (ALT 2022)
Generalization Guarantee of SGD for Pairwise Learning Mingrui Liu , Yiming Ying.Neural Information Processing Systems 35 , 2021. (NeurIPS 2021)
First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems Mingrui Liu , Hassan Rafique, Qihang Lin, Tianbao Yang.Journal of Machine Learning Research , 2021. (JMLR 2021)
Non-Convex Min-Max Optimization: Provable Algorithms and Applications in Machine Learning Mingrui Liu , Qihang Lin, Tianbao Yang.Optimization Methods and Software , 2021.
Improved Schemes for Episodic Memory-based Lifelong Learning Mingrui Liu *, Tianbao Yang, Tajana Rosing. (*: equal contribution) Neural Information Processing Systems 34 , 2020. (NeurIPS 2020) (Spotlight, 3% acceptance rate, top 4% submissions) Code
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets Mingrui Liu , Wei Zhang, Youssef Mroueh, Xiaodong Cui, Jerret Ross, Tianbao Yang, Payel Das.Neural Information Processing Systems 34 , 2020. (NeurIPS 2020)
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks Mingrui Liu , Zhuoning Yuan, Li Shen, Wei Liu, Tianbao Yang.International Conference on Machine Learning , 2020. (ICML 2020) Code
Stochastic AUC Maximization with Deep Neural Networks Mingrui Liu , Zhuoning Yuan, Yiming Ying, Tianbao Yang.International Conference on Learning Representations , 2020. (ICLR 2020) Code
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets Mingrui Liu , Youssef Mroueh, Jerret Ross, Wei Zhang, Xiaodong Cui, Payel Das, Tianbao Yang.International Conference on Learning Representations , 2020. (ICLR 2020)
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization Mingrui Liu , Zhe Li, Xiaoyu Wang, Jinfeng Yi, Tianbao Yang.Neural Information Processing Systems 32 , 2018. (NeurIPS 2018)
arXiv Version Supplement Bibtex Poster
Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions Mingrui Liu , Xiaoxuan Zhang, Lijun Zhang, Rong Jin, Tianbao Yang.Neural Information Processing Systems 32 , 2018. (NeurIPS 2018)
arXiv Version Supplement Bibtex Poster
Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization Mingrui Liu* , Xiaoxuan Zhang*, Xun Zhou, Tianbao Yang. (*: equal contribution)Neural Information Processing Systems 32 , 2018. (NeurIPS 2018)
Supplement
Fast Stochastic AUC Maximization with O(1/n) Convergence Rate Mingrui Liu , Xiaoxuan Zhang, Zaiyi Chen, Xiaoyu Wang, Tianbao Yang.International Conference on Machine Learning 35 , 2018. (ICML 2018)
Supplement Bibtex Poster Code
Stochastic Non-convex Optimization with Strong
High Probability Second-order Convergence Mingrui Liu , Tianbao Yang.arXiv Version
Adaptive Accelerated Gradient Converging Methods under Holderian Error Bound Condition Mingrui Liu , Tianbao Yang.Neural Information Processing Systems 31 , 2017. (NIPS 2017)
Supplement Bibtex Poster arXiv Version
ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization Mingrui Liu , Qihang Lin, Tianbao Yang.Neural Information Processing Systems 31 , 2017. (NIPS 2017)Supplement Bibtex Poster
