paper-with-me

Papers

Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm

2023-11-07 · Stephan Eckstein

Motivated by the entropic optimal transport problem in unbounded settings, we study versions of Hilbert's projective metric for spaces of integrable functions of bounded growth. These versions of Hilbert's metric originate from cones which are relaxations of the cone of all non-negative functions, in the sense that they include all functions having non-negative integral values when multiplied with certain test functions. We show that kernel integral operators are contractions with respect to suitable specifications of such metrics even for kernels which are not bounded away from zero, provided that the decay to zero of the kernel is controlled. As an application to entropic optimal transport, we show exponential convergence of Sinkhorn's algorithm in settings where the marginal distributions have sufficiently light tails compared to the growth of the cost function.

📄 PDF Abstract BibTeX arXiv:2311.04041

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the stability test for reproducing kernel Hilbert spaces

2023-05-01 · Mauro Bisiacco, Gianluigi Pillonetto

Reproducing kernel Hilbert spaces (RKHSs) are special Hilbert spaces where all the evaluation functionals are linear and bounded. They are in one-to-one correspondence with positive definite maps called kernels. Stable R…

Clustering in Hilbert simplex geometry

2017-04-03 · Frank Nielsen, Ke Sun

Clustering categorical distributions in the finite-dimensional probability simplex is a fundamental task met in many applications dealing with normalized histograms. Traditionally, the differential-geometric structures o…

Clustering

Reproducing Kernel Hilbert Space, Mercer's Theorem, Eigenfunctions, Nyström Method, and Use of Kernels in Machine Learning: Tutorial and Survey

2021-06-15 · Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

This is a tutorial and survey paper on kernels, kernel methods, and related fields. We start with reviewing the history of kernels in functional analysis and machine learning. Then, Mercer kernel, Hilbert and Banach spac…

BIG-bench Machine LearningDimensionality ReductionLow-Rank Matrix Completion

Equilibrium existence in a discrete-time endogenous growth model with physical and human capital

2023-12-30 · Luis Alcala

This paper studies a discrete-time version of the Lucas-Uzawa endogenous growth model with physical and human capital in the presence of externalities. Existence of an optimal equilibrium is proved using tools from dynam…

Composition operators on reproducing kernel Hilbert spaces with analytic positive definite functions

2019-11-27 · Masahiro Ikeda, Isao Ishikawa, Yoshihiro Sawano

In this paper, we specify what functions induce the bounded composition operators on a reproducing kernel Hilbert space (RKHS) associated with an analytic positive definite function defined on $\mathbf{R}^d$. We prove th…