AI RESEARCH
Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
arXiv CS.AI
•
ArXi:2603.20656v1 Announce Type: cross We propose a dense associative memory for empirical measures (weighted point clouds). d patterns and queries are finitely ed probability measures, and retrieval is defined by minimizing a Hopfield-style log-sum-exp energy built from the debiased Sinkhorn divergence. We derive retrieval dynamics as a spherical Hellinger Kantorovich (SHK) gradient flow, which updates both locations and weights.