Results 11 to 20 of about 3,323 (160)

The Bregman chord divergence [PDF]

, 2018
Distances are fundamental primitives whose choice significantly impacts the performances of algorithms in machine learning and signal processing. However selecting the most appropriate distance for a given task is an endeavor.
A Banerjee, A Banerjee, F Nielsen, F Nielsen, F Nielsen, F Nielsen, I Csiszár, I Csiszár, I Csiszár, J Burbea, J Jiao, J Naudts, J Zhang, JLWV Jensen, LM Bregman, M Basseville, M Broniatowski, MC Pardo, MM Deza, R Nock, S Amari, SI Amari, SM Ali, TM Cover, V Kac, W Stummer   +25 more
core   +2 more sources

Learning to Approximate a Bregman Divergence [PDF]

CoRR, 2020
Bregman divergences generalize measures such as the squared Euclidean distance and the KL divergence, and arise throughout many areas of machine learning.
Castanon, David, Kulis, Brian, Saligrama, Venkatesh, Siahkamari, Ali, Xia, Xide   +4 more
core   +4 more sources

Information Geometry for Radar Target Detection with Total Jensen–Bregman Divergence [PDF]

Entropy, 2018
This paper proposes a radar target detection algorithm based on information geometry. In particular, the correlation of sample data is modeled as a Hermitian positive-definite (HPD) matrix. Moreover, a class of total Jensen–Bregman divergences, including
Xiaoqiang Hua, Haiyan Fan, Yongqiang Cheng, Hongqiang Wang, Yuliang Qin   +4 more
doaj   +2 more sources

Topological Data Analysis with Bregman Divergences [PDF]

CoRR, 2016
Given a finite set in a metric space, the topological analysis generalizes hierarchical clustering using a 1-parameter family of homology groups to quantify connectivity in all dimensions.
Edelsbrunner, Herbert, Wagner, Hubert
core   +7 more sources

On Minimum Bregman Divergence Inference

Mathematics
The density power divergence (DPD) is a well-studied member of the Bregman divergence family and forms the basis of widely used minimum divergence estimators that balance efficiency and robustness. In this paper, we introduce and study a new sub-class of
Soumik Purkayastha, Ayanendranath Basu
doaj   +3 more sources

On the Jensen-Shannon Symmetrization of Distances Relying on Abstract Means. [PDF]

Entropy (Basel), 2019
The Jensen-Shannon divergence is a renown bounded symmetrization of the unbounded Kullback-Leibler divergence which measures the total Kullback-Leibler divergence to the average mixture distribution. However the Jensen-Shannon divergence between Gaussian
Nielsen F.
europepmc   +2 more sources

Divergence and Sufficiency for Convex Optimization

Entropy, 2017
Logarithmic score and information divergence appear in information theory, statistics, statistical mechanics, and portfolio theory. We demonstrate that all these topics involve some kind of optimization that leads directly to regret functions and such ...
Peter Harremoës
doaj   +5 more sources

The Information Geometry of Bregman Divergences and Some Applications in Multi-Expert Reasoning

Entropy, 2014
The aim of this paper is to develop a comprehensive study of the geometry involved in combining Bregman divergences with pooling operators over closed convex sets in a discrete probabilistic space. A particular connection we develop leads to an iterative
Martin Adamčík
exaly   +3 more sources

Adaptive Mixture Methods Based on Bregman Divergences [PDF]

Digital Signal Processing, 2012
We investigate adaptive mixture methods that linearly combine outputs of $m$ constituent filters running in parallel to model a desired signal. We use "Bregman divergences" and obtain certain multiplicative updates to train the linear combination weights
Arenas-Garcia, Arenas-Garcia, Arenas-Garcia, Bermudez, Bershad, Boukis, Cesa-Bianchi, Fisher, Helmbold, Helmbold, Huseyin A. Inan, Jelfs, Joanes, Kivinen, Kozat, Kozat, Mehmet A. Donmez, Nascimento, Naylor, Sayed, Suleyman S. Kozat, Vovk   +21 more
core   +5 more sources

Maximizing the Bregman divergence from a Bregman family [PDF]

Kybernetika, 2020
11 pages, 5 theorems, no ...
Johannes Rauh, Frantisek Matús
openaire   +4 more sources