Mingrui Liu

On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness

Bilevel Optimization with Lower-Level Uniform Convexity: Theory and Algorithm

An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants

Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training

BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining

Modality-Inconsistent Continual Learning of Multimodal Large Language Models

Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA

Provable Weak-to-Strong Generalization via Overspecified Students and Underspecified Teachers

Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization

Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

Personalized Federated Fine-tuning for Heterogeneous Data: a Two-Level Low Rank Adaptation Approach

On the Convergence of Adam-Type Algorithms for Bilevel Optimization under Unbounded Smoothness