English

Bidirectional Mamba state-space model for anomalous diffusion

Soft Condensed Matter 2024-12-11 v1 Biological Physics Optics Machine Learning

Abstract

Characterizing anomalous diffusion is crucial in order to understand the evolution of complex stochastic systems, from molecular interactions to cellular dynamics. In this work, we characterize the performances regarding such a task of Bi-Mamba, a novel state-space deep-learning architecture articulated with a bidirectional scan mechanism. Our implementation is tested on the AnDi-2 challenge datasets among others. Designed for regression tasks, the Bi-Mamba architecture infers efficiently the effective diffusion coefficient and anomalous exponent from single, short trajectories. As such, our results indicate the potential practical use of the Bi-Mamba architecture for anomalousdiffusion characterization.

Keywords

Cite

@article{arxiv.2412.07299,
  title  = {Bidirectional Mamba state-space model for anomalous diffusion},
  author = {Maxime Lavaud and Yosef Shokeeb and Juliette Lacherez and Yacine Amarouchene and Thomas Salez},
  journal= {arXiv preprint arXiv:2412.07299},
  year   = {2024}
}
R2 v1 2026-06-28T20:29:08.559Z