AI & ML
On sparsity, extremal structure, and monotonicity properties of Wasserstein and Gromov-Wasserstein optimal transport plans
arXiv stat.ML0 views
arXiv:2602.16265v3 Announce Type: replace Abstract: This note gives a self-contained overview of some key properties of the Gromov-Wasserstein (GW) distance, compared with the standard linear optimal transport (OT) framework. More specifically, I explore the following questions: are GW optimal transport plans sparse? under what conditions does there exist an optimal plan supported on a permutation? do optimal plans satisfy a form of cyclical monotonicity? In particular, I present the conditionally negative/positive definite (CND/CPD) properties and show that, when they hold, there exist GW optimal plans that are sparse and supported on a permutation. In the last section, I also give examples where no permutation is optimal when the CND or CPD assumption is dropped.
Source:https://arxiv.org/abs/2602.16265PreviousRecovering the Euclidean Geometry of High-Dimensional Data Under Heterogeneous NoiseNextAuto-differentiable data assimilation: Co-learning of states, dynamics, and filtering algorithms
Related posts
Your enterprise AI access can be sold for pennies – beware ‘LLM Mixers’
0ZDNet
Quantum neural networks with high-dimensional quantum neurons
0Phys.org Tech
Less data, faster discovery: Researchers rethink AI's role in developing new materials
0Phys.org Tech
What makes 'super shoes' so fast?
0Phys.org Tech

Amazon’s Starlink rival sees major setback after 40 satellites destroyed in rocket failure
0Tom's Hardware

Unlock Tom's Hardware Premium's SuperComputer 2026 coverage for free — sign up for an account to read detailed reports from the show
0Tom's Hardware