Wasserstein Riemannian Geometry of Positive-definite Matrices∗

نویسندگان

  • Luigi Malagò
  • Luigi Montrucchio
  • Giovanni Pistone
چکیده

The Wasserstein distance on multivariate non-degenerate Gaussian densities is a Riemannian distance. After reviewing the properties of the distance and the metric geodesic, we derive an explicit form of the Riemannian metrics on positive-definite matrices and compute its tensor form with respect to the trace scalar product. The tensor is a matrix, which is the solution of a Lyapunov equation. We compute explicit form for the Riemannian exponential, the normal coordinates charts, the Riemannian gradient, and discuss the gradient flow of the entropy. Finally, the Levi-Civita covariant derivative is computed in matrix form together with the differential equation for the parallel transport. While all computations are given in matrix form, notheless we discuss the use of a special moving frame. Applications are briefly discussed.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Riemannian Manifold Kernel for Persistence Diagrams

Algebraic topology methods have recently played an important role for statistical analysis with complicated geometric structured data. Among them, persistent homology is a well-known tool to extract robust topological features, and outputs as persistence diagrams. Unfortunately, persistence diagrams are point multi-sets which can not be used in machine learning algorithms for vector data. To de...

متن کامل

Riemannian Metric Learning for Symmetric Positive Definite Matrices

Over the past few years, symmetric positive definite matrices (SPD) have been receiving considerable attention from computer vision community. Though various distance measures have been proposed in the past for comparing SPD matrices, the two most widely-used measures are affine-invariant distance and log-Euclidean distance. This is because these two measures are true geodesic distances induced...

متن کامل

Symmetric Positive-Definite Matrices: From Geometry to Applications and Visualization

In many engineering applications that use tensor analysis, such as tensor imaging, the underlying tensors have the characteristic of being positive definite. It might therefore be more appropriate to use techniques specially adapted to such tensors. We will describe the geometry and calculus on the Riemannian symmetric space of positive-definite tensors. First, we will explain why the geometry,...

متن کامل

A Geometry Preserving Kernel over Riemannian Manifolds

Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...

متن کامل

Geometric distance and mean for positive semi-definite matrices of fixed rank

This paper introduces a new distance and mean on the set of positive semi-definite matrices of fixed-rank. The proposed distance is derived from a well-chosen Riemannian quotient geometry that generalizes the reductive geometry of the positive cone and the associated natural metric. The resulting Riemannian space has strong geometrical properties: it is geodesically complete, and the metric is ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2018