Search Results for author: Tomohiro Nishiyama

Found 7 papers, 3 papers with code

Lower Bounds for the Total Variation Distance Given Means and Variances of Distributions

1 code implementation12 Dec 2022 Tomohiro Nishiyama

For arbitrary two probability measures on real d-space with given means and variances (covariance matrices), we provide lower bounds for their total variation distance.

Convex Optimization on Functionals of Probability Densities

no code implementations16 Feb 2020 Tomohiro Nishiyama

In information theory, some optimization problems result in convex optimization problems on strictly convex functionals of probability densities.

A New Lower Bound for Kullback-Leibler Divergence Based on Hammersley-Chapman-Robbins Bound

1 code implementation29 Jun 2019 Tomohiro Nishiyama

By using the relation between the KL-divergence and the Chi-square divergence, we show that the lower bound for the KL-divergence which only depends on the expectation value and the variance of a function we choose.

Divergence Network: Graphical calculation method of divergence functions

no code implementations30 Oct 2018 Tomohiro Nishiyama

In this paper, we introduce directed networks called `divergence network' in order to perform graphical calculation of divergence functions.

Sum decomposition of divergence into three divergences

no code implementations3 Oct 2018 Tomohiro Nishiyama

Divergence functions play a key role as to measure the discrepancy between two points in the field of machine learning, statistics and signal processing.

BIG-bench Machine Learning

Generalized Bregman and Jensen divergences which include some f-divergences

no code implementations19 Aug 2018 Tomohiro Nishiyama

In this paper, we introduce new classes of divergences by extending the definitions of the Bregman divergence and the skew Jensen divergence.

Cannot find the paper you are looking for? You can Submit a new open access paper.