Search Results for author:
Found 1 papers, 0 papers with code
Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy
Recently, sharpness-aware minimization (SAM) has attracted a lot of attention because of its surprising effectiveness in improving generalization performance. However, training neural networks with SAM can be highly unstable since the loss does not decrease along the direction of the exact gradient at the current point, but instead follows the direction of a surrogate gradient evaluated at another point nearby.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
