Papers
1
Total Citations
2
H-Index
1
About
Nina Miolane is a leading researcher at the intersection of geometric statistics, machine learning, and medical imaging. Her work fundamentally advances how we analyze complex, non-Euclidean data—particularly shapes and deformations modeled on Lie groups. Her foundational paper, "Statistics on Lie groups: A need to go beyond the pseudo-Riemannian framework" (2015, 2 citations), critically re-examined the mathematical foundations for computing statistics on these curved spaces, moving beyond traditional Riemannian approaches to better capture the true geometry of anatomical variability. This contribution is pivotal for Computational Anatomy, where organ shapes are modeled as deformations of a reference. Beyond this theoretical work, Miolane is the creator and lead developer of Geomstats, an open-source Python package that democratizes geometric statistics for the broader machine learning community. Her impact is measured not only in citations but in the adoption of her tools and frameworks, which empower researchers across fields to perform statistics on manifolds, from shape analysis in biology to pose estimation in robotics.
Research Focus
Key Achievements
Top Papers
- 1