Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when the data lies on a curved manifold -- requiring a Riemannian metric to describe the space's local curvature. Estimating such a metric, however, remains a major challenge in high dimensions.

@article{béthune2025_2505.18230,
  title={ Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models },
  author={ Louis Béthune and David Vigouroux and Yilun Du and Rufin VanRullen and Thomas Serre and Victor Boutin },
  journal={arXiv preprint arXiv:2505.18230},
  year={ 2025 }
}