Search Results for author:
Found 2 papers, 0 papers with code
A Precise Characterization of SGD Stability Using Loss Surface Geometry
In this paper, we delve deeper into the relationship between linear stability and sharpness.
mSAM: Micro-Batch-Averaged Sharpness-Aware Minimization
Modern deep learning models are over-parameterized, where different optima can result in widely varying generalization performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
