Showing 2025Show all
2 papers · 1 filter
math.NA2025
Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability
Mitchell Scott, Tianshi Xu, Ziyuan Tang +4
Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise. We analyze preconditioned SGD in the geometry induced b…
math.NA2025
Mixed Precision Orthogonalization-Free Projection Methods for Eigenvalue and Singular Value Problems
Tianshi Xu, Zechen Zhang, Jie Chen +2
Mixed-precision arithmetic offers significant computational advantages for large-scale matrix computation tasks, yet preserving accuracy and stability in eigenvalue problems and th…