Procrustes Metrics on Covariance Operators and Optimal Transportation of Gaussian Processes
نویسندگان
چکیده
منابع مشابه
Continuity, Curvature, and the General Covariance of Optimal Transportation
Let M and M̄ be n-dimensional manifolds equipped with suitable Borel probability measures ρ and ρ̄. For subdomains M and M̄ of Rn, Ma, Trudinger & Wang gave sufficient conditions on a transportation cost c ∈ C4(M × M̄) to guarantee smoothness of the optimal map pushing ρ forward to ρ̄; the necessity of these conditions was deduced by Loeper. The present manuscript shows the form of these conditions ...
متن کاملsome properties of fuzzy hilbert spaces and norm of operators
in this thesis, at first we investigate the bounded inverse theorem on fuzzy normed linear spaces and study the set of all compact operators on these spaces. then we introduce the notions of fuzzy boundedness and investigate a new norm operators and the relationship between continuity and boundedness. and, we show that the space of all fuzzy bounded operators is complete. finally, we define...
15 صفحه اولTruncated Covariance Matrices and Toeplitz Methods in Gaussian Processes
Gaussian processes are a limit extension of neural networks. Standard Gaussian process techniques use a squared exponential covariance function. Here, the use of truncated covariances is proposed. Such cov-ariances have compact support. Their use speeds up matrix inversion and increases precision. Furthermore they allow the use of speedy, memory eecient Toeplitz inversion for high dimensional g...
متن کاملThe Rate of Entropy for Gaussian Processes
In this paper, we show that in order to obtain the Tsallis entropy rate for stochastic processes, we can use the limit of conditional entropy, as it was done for the case of Shannon and Renyi entropy rates. Using that we can obtain Tsallis entropy rate for stationary Gaussian processes. Finally, we derive the relation between Renyi, Shannon and Tsallis entropy rates for stationary Gaussian proc...
متن کاملLinear-Time Inverse Covariance Matrix Estimation in Gaussian Processes
The computational cost of Gaussian process regression grows cubically with respect to the number of variables due to the inversion of the covariance matrix, which is impractical for data sets with more than a few thousand nodes. Furthermore, Gaussian processes lack the ability to represent conditional independence assertions between variables. We describe iterative proportional scaling for dire...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Sankhya A
سال: 2018
ISSN: 0976-836X,0976-8378
DOI: 10.1007/s13171-018-0130-1