mlsanityData to 14 Oct 2026

From Cone Geometry to Monge Structure: Local Defects and Global Regret in High-Dimensional Optimal Transport

arXiv 2606.04695 ↗First posted 3 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Exact optimal transport in high dimensions becomes tractable only when additional structure selects the optimal coupling. Classical Monge transportation solves the discrete problem once a cost array is known to be Monge, but it does not explain when geometry in the original feature space creates that structure. We characterize this regime for cone-induced orders and squared Mahalanobis costs: Macuteness of the cone is equivalent to the Monge property of every cross-cost matrix generated by two cone chains, after which classical northwest-corner optimality gives exact transport. When the inequalities fail, we derive an exact variational representation of northwestcorner regret over a marginal-dependent cumulative-deficit polytope. Its Fr'echet box relaxation yields a projection-free, marginal-weighted localdefect bound; we characterize when the relaxation is exact and prove that it is worst-case sharp when only local defect budgets are known. We further show that the worst-case defect patterns can be realized by genuine squared-Euclidean cross-costs. Finally, Mahalanobis distances of observed increments to the cone control the local defects, while a strict geometric margin gives an explicit radius of exact stability. The resulting theory links high-dimensional ground-space geometry to exact Monge transport and quantifies the global loss induced by local departures from ordered structure.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 50 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

22 of 50 references.

References · 22

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  5. 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 292
  6. 2017Near-linear time approximation algorithms for optimal transport via Sinkhorn iterationcited by 223
  7. 2019Generalized Sliced Wasserstein Distancescited by 208
  8. 2018Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learningcited by 56
  9. 2019Tree-Sliced Variants of Wasserstein Distancescited by 54
  10. 2016Causal transport in discrete time and applicationscited by 21
  11. 2018Existence, Duality, and Cyclical monotonicity for weak transport costscited by 21
  12. 2026FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPUcited by 11
10 more
  1. 2023Optimal Transport for Measures with Noisy Tree Metriccited by 7
  2. 2024Tree-Sliced Wasserstein Distance: A Geometric Perspectivecited by 7
  3. 2023Learning Elastic Costs to Shape Monge Displacementscited by 6
  4. 2019Estimation of Monge Matricescited by 4
  5. 2021Order Constraints in Optimal Transportcited by 4
  6. 2025Distance-Based Tree-Sliced Wasserstein Distancecited by 4
  7. 2025Tree-Sliced Wasserstein Distance with Nonlinear Projectioncited by 3
  8. 2020The Directional Optimal Transportcited by 2
  9. 2026Revisiting transportation problems under Monge costs with applications to location problemscited by 1
  10. 2026Active Seriation: Efficient Ordering Recovery with Statistical Guaranteescited by 1

Built on by

Not cited yet.