The theme of this volume is the application of the rich and powerful theories and techniques of Riemannian geometry to the problems in machine learning, statistics, optimization, computer vision, and related fields. Traditional machine learning and data analysis methods often assume that the input data can be represented by vectors in Euclidean space. While this assumption has worked well for many applications, researchers have increasingly realized that if the data is intrinsically non-Euclidean, ignoring this geometrical structure can lead to suboptimal results.
Learning, F. M., & Vision, C. (2016). Algorithmic Advances in Riemannian Geometry and Applications, 145–172. Retrieved from http://link.springer.com/10.1007/978-3-319-45026-1