Linear Diffusion Networks
Machine Learning
2025-03-27 v4
Abstract
We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a diffusion-inspired attention mechanism. This design enables efficient global information propagation while preserving fine-grained temporal details. LDN overcomes the limitations of conventional recurrent and transformer models by allowing full parallelization across time steps and supporting robust multi-scale temporal representations. Experiments on benchmark sequence modeling tasks demonstrate that LDN delivers competitive performance across ImageNet and LRA tasks.
Cite
@article{arxiv.2502.12381,
title = {Linear Diffusion Networks},
author = {Jacob Fein-Ashley},
journal= {arXiv preprint arXiv:2502.12381},
year = {2025}
}