We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence. Based on a Frank-Wolfe optimization strategy, our approach proceeds by populating the support of the barycenter incrementally, without requiring any pre-allocation.

Cohen et al. (2021) empirically study the evolution of the largest eigenvalue of the loss Hessian, also known as sharpness, along the gradient descent (GD) trajectory and observe the Edge of Stability (EoS) phenomenon.

To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/