arXiv Machine Learning July 17, 2026 By Thomas Weighill, Chidinma Williams

Measuring Spatial Clustering via Metropolis-Hastings Diffusion Distance

Read the original on arXiv Machine Learning →

arXiv:2607. 14880v1 Announce Type: cross Abstract: We propose a novel measure of the discrepancy between two probability distributions $f$ and $g$ on a graph - which we call the diffusion distance - that measures the rate of convergence of $f$ to $g$ under a graph-constrained Markov chain with stationary distribution $g$.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

Jul 9

Fast determinantal sampling on general spaces and diffusion geometry

arXiv:2607. 06644v1 Announce Type: cross Abstract: Determinantal point processes have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and other compact representations of large-scale datasets.

By Hoang-Son Tran, Pranav Gupta, Subhroshekhar Ghosh

diffusion

arXiv AI

Jul 9

Diffusion enabled Optimal Transport distances for graph matching

arXiv:2607. 06646v1 Announce Type: cross Abstract: This paper introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method for graph comparison that unifies node features and structural connectivity through optimal transport.

By Iman Seyedi, Francesco Archetti

diffusion

arXiv Machine Learning

Jul 27

Distributional Determinantal Point Process for Repulsive Clustering of Distributions

arXiv:2607. 21847v1 Announce Type: cross Abstract: We introduce the distributional determinantal point process (dDPP) as a novel repulsive point process whose atoms are probability distributions rather than points in a real space.

By Khai Nguyen, Yang Ni, Elizabeth Juarez-Colunga, Peter Mueller

arXiv Machine Learning

Aug 10

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.

By Iskander Azangulov, George Deligiannidis, Judith Rousseau

diffusion benchmarks

arXiv Machine Learning

Jul 8

EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning

arXiv:2607. 06497v1 Announce Type: new Abstract: We introduce EntroPath, a manifold learning method that recovers geodesic geometry from data graphs through ensembles of diffusion paths.

By Przemys{\l}aw Rola

rag diffusion benchmarks

arXiv Machine Learning

Jul 24

Conditional Entropy of Heat Diffusion on Temporal Networks

arXiv:2605. 21514v2 Announce Type: replace-cross Abstract: Diffusion-based information-theoretic approaches provide new theoretical and practical tools to study complex networks.

By Samuel Koovely, Alexandre Bovet

diffusion benchmarks safety

Related stories

Fast determinantal sampling on general spaces and diffusion geometry

Diffusion enabled Optimal Transport distances for graph matching

Distributional Determinantal Point Process for Repulsive Clustering of Distributions

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

EntroPath: Maximum Entropy Path Ensemble Embedding for Manifold Learning

Conditional Entropy of Heat Diffusion on Temporal Networks