arXiv subjects

Michael M Bronstein

Publications and source records attributed to Michael M Bronstein.

3 recordsLinked to original sources

arXiv2024

To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models

Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into a Gaussian. Samples from the generative model are then obtained by simulating an approximation of the time reversal of this diffusion initialized by Gaussian samples. Recent research has explored adapting diffusion models for sampling and inference tasks. In this paper, we leverage known connections to stochastic control akin to the Föllmer drift to extend established neural network approximation results for the Föllmer drift to denoising diffusion models and samplers.

stat.ML↗

arXiv2021

Beltrami Flow and Neural Diffusion on Graphs

We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positional encodings derived from the graph topology and jointly evolved by the Beltrami flow, producing simultaneously continuous feature learning and topology evolution. The resulting model generalises many popular graph neural networks and achieves state-of-the-art results on several benchmarks.

cs.LG↗

arXiv2011

Kernel diff-hash

This paper presents a kernel formulation of the recently introduced diff-hash algorithm for the construction of similarity-sensitive hash functions. Our kernel diff-hash algorithm that shows superior performance on the problem of image feature descriptor matching.

cs.CV↗