Mingrui Liu

5

Papers

11

Total Citations

Papers (5)

Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization

NeurIPS 2025arXiv

A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective