← Authors

Mingrui Liu

33 papers · 2017–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (38) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (8) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (4) 🀝 Dynamic Duo (12) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (17) πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (109) πŸ“ˆ Trend Setter ⚑ Prolific Year (6) πŸ”₯ Unstoppable (6) πŸ’Ž Century Club (33)

Conferences

NIPS (16) ICLR (6) ICML (6) ALT (2) AAAI (1) JMLR (1) UAI (1)

Top co-authors

Tianbao Yang (12) Michael Crawshaw (9) Yajie Bao (5) Jie Hao (5) Xiaochuan Gong (3) Xiaoxuan Zhang (3) Francesco Orabona (3) Wei Zhang (3) Blake Woodworth (2) Youssef Mroueh (2)

Keywords

non-convex optimization (7) stochastic gradient descent (6) federated learning (5) stochastic optimization (5) convergence rate (4) convex optimization (4) learning theory (3) min-max optimization (3) auc maximization (3) communication efficiency (3) gradient clipping (3) continual learning (3) bilevel optimization (3) unbounded smoothness (3) nonconvex optimization (2) client participation (2) recurrent neural network (2) distributed learning (2) gradient descent (2) generative adversarial network (2)

Papers

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability ICML 2025
Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression ICLR 2025
Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness ICLR 2025
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis ICLR 2024
Algorithmic Foundation of Federated Learning with Sequential Data AAAI 2024
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis NIPS 2024
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness NIPS 2024
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness ICML 2024
Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective ICML 2024
AUC Maximization in Imbalanced Lifelong Learning UAI 2023
Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds NIPS 2023
Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization NIPS 2023
Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm NIPS 2023
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data ICLR 2023
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks NIPS 2022
Fast Composite Optimization and Statistical Recovery in Federated Learning ICML 2022
Will Bilevel Optimizers Benefit from Loops NIPS 2022
On the Last Iterate Convergence of Momentum Methods ALT 2022
On the Initialization for Convex-Concave Min-max Problems ALT 2022
Robustness to Unbounded Smoothness of Generalized SignSGD NIPS 2022
First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems JMLR 2021
Generalization Guarantee of SGD for Pairwise Learning NIPS 2021
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets NIPS 2020
Improved Schemes for Episodic Memory-based Lifelong Learning NIPS 2020
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks ICML 2020
Stochastic AUC Maximization with Deep Neural Networks ICLR 2020
Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets ICLR 2020
Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions NIPS 2018
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization NIPS 2018
Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate ICML 2018
Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization NIPS 2018
Adaptive Accelerated Gradient Converging Method under H\"{o}lderian Error Bound Condition NIPS 2017
ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization NIPS 2017