AI RESEARCH

Deep Kuratowski Embedding Neural Networks for Wasserstein Metric Learning

arXiv CS.LG

ArXi:2604.04343v1 Announce Type: new Computing pairwise Wasserstein distances is a fundamental bottleneck in data analysis pipelines. Motivated by the classical Kuratowski embedding theorem, we propose two neural architectures for learning to approximate the Wasserstein-2 distance ($W_2$) from data. The first, DeepKENN, aggregates distances across all intermediate feature maps of a CNN using learnable positive weights.