Ganzhao Yuan

A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints

Layerwise Learning Rate in the Era of Large Language Models

On the Convergence of Muon and Beyond

Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization

AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs

ADMM for Structured Fractional Minimization

MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization

ADMM for Nonconvex Optimization under Minimal Continuity Assumption

Block Coordinate Descent Methods for Optimization under J-Orthogonality Constraints with Applications

A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints

ADMM for Nonsmooth Composite Optimization under Orthogonality Constraints