Stabilizing sharpness-aware minimization through a simple renormalization strategy
From MaRDI portal
Cites work
- 10.1162/153244302760200704
- Adaptive subgradient methods for online learning and stochastic optimization
- Advancing mathematics by guiding human intuition with AI
- Convex optimization: algorithms and complexity
- Entropy-SGD: biasing gradient descent into wide valleys
- Optimization methods for large-scale machine learning
This page was built for publication: Stabilizing sharpness-aware minimization through a simple renormalization strategy
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6947075)