Bregman divergences - Open Access .click

Results 51 to 60 of about 3,294 (168)

Coherent Forecasting of Realized Volatility

Journal of Forecasting, EarlyView.
ABSTRACT The QLIKE loss function is the stylized favorite of the literature on volatility forecasting when it comes to out‐of‐sample evaluation and the state of the art model for realized volatility (RV) forecasting is the HAR model, which minimizes the squared error loss for in‐sample estimation of the parameters.
Marius Puke, Karsten Schweikert
wiley +1 more source

Information Measures: the Curious Case of the Binary Alphabet

, 2014
Four problems related to information divergence measures defined on finite alphabets are considered. In three of the cases we consider, we illustrate a contrast which arises between the binary-alphabet and larger-alphabet settings.
Courtade, Thomas +4 more
core +1 more source

Genome‐Wide Assessment Reveals Ancestral Differences in Homozygosity Patterns Potentially Linked to Parkinson's Disease Etiology

Movement Disorders, EarlyView.
Abstract Background Recessive genetic variation and extended runs of homozygosity (ROHs) may contribute to the unexplained heritability of Parkinson's disease (PD), particularly in diverse and understudied populations. Objective We conducted the first large‐scale, multi‐ancestral investigation of PD to examine the impact of genome‐wide homozygosity on ...
Kathryn Step +680 more
wiley +1 more source

Proper scoring rules and Bregman divergence

Bernoulli, 2018
We revisit the mathematical foundations of proper scoring rules (PSRs) and Bregman divergences and present their characteristic properties in a unified theoretical framework. In many situations it is preferable not to generate a PSR directly from its convex entropy on the unit simplex but instead by the sublinear extension of the entropy to the ...
openaire +3 more sources

Matrix Nearness Problems with Bregman Divergences [PDF]

SIAM Journal on Matrix Analysis and Applications, 2008
This paper discusses a new class of matrix nearness problems that measure approximation error using a directed distance measure called a Bregman divergence. Bregman divergences offer an important generalization of the squared Frobenius norm and relative entropy, and they all share fundamental geometric properties.
Dhillon, Inderjit S., Tropp, Joel A.
openaire +2 more sources

Existence Analysis of a Three‐Species Memristor Drift‐Diffusion System Coupled to Electric Networks

Mathematical Methods in the Applied Sciences, EarlyView.
ABSTRACT The existence of global weak solutions to a partial‐differential‐algebraic system is proved. The system consists of the drift‐diffusion equations for the electron, hole, and oxide vacancy densities in a memristor device, the Poisson equation for the electric potential, and the differential‐algebraic equations for an electric network.
Ansgar Jüngel, Tuấn Tùng Nguyến
wiley +1 more source

The Duality of Entropy/Extropy, and Completion of the Kullback Information Complex

Entropy, 2018
The refinement axiom for entropy has been provocative in providing foundations of information theory, recognised as thoughtworthy in the writings of both Shannon and Jaynes.
Frank Lad, Giuseppe Sanfilippo, Gianna Agrò +2 more
doaj +1 more source

Neural Bregman Divergences for Distance Learning

, 2022
Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space.
Lu, Fred, Raff, Edward, Ferraro, Francis
openaire +2 more sources

Linking regional and global functional trait data: insights from mammal communities in a fragmented Atlantic Forest landscape

Oikos, EarlyView.
Accurate functional trait data are essential for understanding ecosystem services and processes in fragmented landscapes. We evaluated whether the global EltonTraits 1.0 database adequately represents the functional structure of mammal communities in forest fragments and restoration sites in a highly fragmented Atlantic Forest landscape.
Maria F. R. Godoi +5 more
wiley +1 more source

Preconditioner Design via the Bregman Divergence

, 2023
We study a preconditioner for a Hermitian positive definite linear system, which is obtained as the solution of a matrix nearness problem based on the Bregman log determinant divergence. The preconditioner is of the form of a Hermitian positive definite matrix plus a low-rank matrix.
Bock, Andreas, Andersen, Martin S.
openaire +2 more sources

bregman divergence
fos: computer and information sciences
machine learning cs.lg

computer science - machine learning
information geometry
fos: mathematics

convexity
information theory cs.it
computer science - information theory