Ruoran Xu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric instability.
The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric instability.
Papers
Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
The paper introduces Singularity-aware Adam (S-Adam), a novel optimizer that stabilizes deep learning training in non-smooth loss landscapes by dynamically damping updates based on local geometric ins…