Amortized Projection Optimization for Sliced Wasserstein Generative Models. (arXiv:2203.13417v4 [stat.ML] UPDATED)

Seeking informative projecting directions has been an important task in
utilizing sliced Wasserstein distance in applications. However, finding these
directions usually requires an iterative optimization procedure over the space
of projecting directions, which is computationally expensive. Moreover, the
computational issue is even more severe in deep learning applications, where
computing the distance between two mini-batch probability measures is repeated
several times. This nested loop has been one of the main challenges that
prevent the usage of sliced Wasserstein distances based …

arxiv generative models optimization projection