Gromov-Wasserstein Averaging of Kernel and Distance Matrices
نویسندگان
چکیده
This paper presents a new technique for computing the barycenter of a set of distance or kernel matrices. These matrices, which define the interrelationships between points sampled from individual domains, are not required to have the same size or to be in row-by-row correspondence. We compare these matrices using the softassign criterion, which measures the minimum distortion induced by a probabilistic map from the rows of one similarity matrix to the rows of another; this criterion amounts to a regularized version of the Gromov-Wasserstein (GW) distance between metric-measure spaces. The barycenter is then defined as a Fréchet mean of the input matrices with respect to this criterion, minimizing a weighted sum of softassign values. We provide a fast iterative algorithm for the resulting nonconvex optimization problem, built upon state-ofthe-art tools for regularized optimal transportation. We demonstrate its application to the computation of shape barycenters and to the prediction of energy levels from molecular configurations in quantum chemistry.
منابع مشابه
The Gromov-Wasserstein Distance: A Brief Overview
We recall the construction of the Gromov–Wasserstein distance and concentrate on quantitative aspects of the definition.
متن کاملGromov-Hausdorff Convergence of Discrete Transportation Metrics
This paper continues the investigation of ‘Wasserstein-like’ transportation distances for probability measures on discrete sets. We prove that the discrete transportation metrics on the d-dimensional discrete torus TN with mesh size 1 N converge, when N → ∞, to the standard 2-Wasserstein distance on the continuous torus in the sense of Gromov– Hausdorff. This is the first result of a passage to...
متن کاملA spectral notion of Gromov–Wasserstein distance and related methods
Article history: Received 12 February 2010 Revised 7 August 2010 Accepted 16 September 2010 Available online 29 September 2010 Communicated by Mauro Maggioni
متن کاملWasserstein Distance Measure Machines
This paper presents a distance-based discriminative framework for learning with probability distributions. Instead of using kernel mean embeddings or generalized radial basis kernels, we introduce embeddings based on dissimilarity of distributions to some reference distributions denoted as templates. Our framework extends the theory of similarity of Balcan et al. (2008) to the population distri...
متن کاملRiemannian 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 کاملذخیره 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 2016