Mingrui Liu

Venues

Frequent coauthors

Papers

1. Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension
   COLT 2026 ·

   Michael Crawshaw

   DBLP profile ↗ORCID search ↗
2. Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
   NeurIPS 2025 ·

   Xiaochuan Gong

   DBLP profile ↗ORCID search ↗
3. Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
   ICLR 2025 ·

   Michael Crawshaw

   DBLP profile ↗ORCID search ↗
4. Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability
   ICML 2025 ·

   Michael Crawshaw

   DBLP profile ↗ORCID search ↗
5. Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression
   ICLR 2025 ·

   Michael Crawshaw

   DBLP profile ↗ORCID search ↗
6. A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
   ICML 2024 ·

   Xiaochuan Gong

   DBLP profile ↗ORCID search ↗
7. Algorithmic Foundation of Federated Learning with Sequential Data
   AAAI 2024 · Mingrui Liu
8. An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
   NeurIPS 2024 ·

   Xiaochuan Gong

   DBLP profile ↗ORCID search ↗
9. Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
   ICLR 2024 ·

   Jie Hao

   DBLP profile ↗ORCID search ↗
10. Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
    NeurIPS 2024 ·

    Michael Crawshaw

    DBLP profile ↗ORCID search ↗
11. LESS-Map: Lightweight and Evolving Semantic Map in Parking Lots for Long-term Self-Localization
    ICRA 2024 · Mingrui Liu
12. Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
    ICML 2024 ·

    Yajie Bao

    DBLP profile ↗ORCID search ↗