Re-basin
3 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Re-basin
Most implemented papers
Git Re-Basin: Merging Models modulo Permutation Symmetries
The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease.
Re-basin via implicit Sinkhorn differentiation
fagp/sinkhorn-rebasin
•
•
CVPR 2023
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity.
Rethink Model Re-Basin and the Linear Mode Connectivity
Recent studies suggest that with sufficiently wide models, most SGD solutions can, up to permutation, converge into the same basin.
