Interval semimetric spaces for approximate distances
نویسندگان
چکیده
In accordance with the ideas of Interval Analysis, a notion of interval-valued semimetric space is proposed. Also, the possibility of applying the resulting theory to some chapters of Computer Science is examined.
منابع مشابه
Equivalence of Distance-based and Rkhs-based Statistics in Hypothesis Testing by Dino Sejdinovic, Bharath Sriperumbudur,
We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, maximum mean discrepancies (MMD), that is, distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning. In the ...
متن کاملEquivalence of Distance-based and Rkhs-based Statistics in Hypothesis Testing by Dino Sejdinovic,
We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, maximum mean discrepancies (MMD), that is, distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning. In the ...
متن کاملEquivalence of distance-based and RKHS-based statistics in hypothesis testing
We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, Maximum Mean Discrepancies (MMD), i.e., distances between embeddings of distributions to reproducing kernel Hilbert spaces (RKHS), as established in machine learning. In the cas...
متن کاملRobust Scalable Visualized Clustering in Vector and Non Vector Semi-Metric Spaces
We describe an approach to data analytics on large systems using a suite of robust parallel algorithms running on both clouds and HPC systems. We apply this to cases where the data is defined in a vector space and when only pairwise distances between points are defined. We introduce improvements to known algorithms for functionality, features and performance but review state of the art as this ...
متن کاملInterpolated Discretized Embedding of Single Vectors and Vector Pairs for Classification, Metric Learning and Distance Approximation
We propose a new embedding method for a single vector and for a pair of vectors. This embedding method enables: a) efficient classification and regression of functions of single vectors; b) efficient approximation of distance functions; and c) general, non-Euclidean, semimetric learning. To the best of our knowledge, this is the first work that enables learning any general, non-Euclidean, semim...
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 2005