SOURCE-LINKED INTELLIGENCE

Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Optimal transport (OT) compares distributions and aligns datasets in machine learning, yet unregularized discrete OT requires a linear program with quadratically many transport variables. We propose HELLO, a hierarchical solver that casts large-scale discrete OT as edge localization and uses dual potentials to guide both coarse-to-fine initialization and within-level refinement. Initialization propagates coarse dual potentials across a recursive subsampling hierarchy to assign candidate edges. Refinement then iteratively inserts the largest dual violators in each row and column until the relat

Read original source ↗ Open in workspace

recordType

paper

region

Global