Tag
This paper extends MST-Direct, a method for multivariate geostatistical simulation using Sinkhorn optimal transport, from bivariate unconditional small-grid settings to multivariate, conditional, and large-scale settings, preserving joint distributions exactly and outperforming existing methods.
This paper presents Block-Wise Differentiable Sinkhorn Attention, a method for efficient long-context balanced entropic optimal transport attention on TPU hardware. It introduces a tail-refinement surrogate for exact differentiation, proving an efficient backward pass schedule and demonstrating significant improvements in Pfam sequence alignment reconstruction.