Re-basin via implicit Sinkhorn differentiation

Understand

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.

• However, finding the right permutation is challenging, and current optimization techniques are not differentiable, which makes it difficult to integrate into a gradient-based optimization, and often leads to sub-optimal solutions.
• In this paper, we propose a Sinkhorn re-basin network with the ability to obtain the transportation plan that better suits a given objective.
• Unlike the current state-of-art, our method is differentiable and, therefore, easy to adapt to any task within the deep learning domain.