Copula-MGARCH with continuous covariance decomposition

2015 ◽  
Vol 133 ◽  
pp. 73-76 ◽  
Author(s):  
Helmut Herwartz ◽  
Fabian H.C. Raters
Keyword(s):  
Covariance Decomposition

Bayesian sparse covariance decomposition with a graphical structure

2014 ◽  
Vol 26 (1-2) ◽  
pp. 493-510 ◽  
Author(s):  
Lin Zhang ◽  
Abhra Sarkar ◽  
Bani K. Mallick
Keyword(s):  
Covariance Decomposition ◽  
Graphical Structure

Implementing Negative Correlation Learning in Evolutionary Ensembles with Suitable Speciation Techniques

2008 ◽  
pp. 344-369
Author(s):  
Peter Duell ◽  
Xin Yao
Keyword(s):  
Negative Correlation ◽  
Evolutionary Process ◽  
Future Research ◽  
Fitness Sharing ◽  
Negative Correlation Learning ◽  
Correlation Learning ◽  
Future Research Directions ◽  
Classification Tasks ◽  
Covariance Decomposition ◽  
The Impact

Negative correlation learning (NCL) is a technique that attempts to create an ensemble of neural networks whose outputs are accurate but negatively correlated. The motivation for such a technique can be found in the bias-variance-covariance decomposition of an ensemble of learner’s generalization error. NCL is also increasingly used in conjunction with an evolutionary process, which gives rise to the possibility of adapting the structures of the networks at the same time as learning the weights. This chapter examines the motivation and characteristics of the NCL algorithm. Some recent work relating to the implementation of NCL in a single objective evolutionary framework for classification tasks is presented, and we examine the impact of two speciation techniques: implicit fitness sharing and an island model population structure. The choice of such speciation techniques can have a detrimental effect on the ability of NCL to produce accurate and diverse ensembles and should therefore be chosen carefully. This chapter also provides an overview of other researchers’ work with NCL and gives some promising future research directions.

Modelling variability in initial parameters for the simulation of rough rice drying using the covariance decomposition algorithm

2008 ◽  
Vol 100 (1) ◽  
pp. 53-57 ◽  
Author(s):  
Fumihiko Tanaka ◽  
Kazuo Morita ◽  
Hiroyuki Sekiya ◽  
Naoya Izumi ◽  
Toshitaka Uchino ◽  
...  
Keyword(s):  
Decomposition Algorithm ◽  
Rough Rice ◽  
Covariance Decomposition ◽  
Rice Drying

scholarly journals <i>De praeceptis ferendis</i>: good practice in multi-model ensembles

2014 ◽  
Vol 14 (11) ◽  
pp. 15803-15865 ◽  
Author(s):  
I. Kioutsioukis ◽  
S. Galmarini
Keyword(s):  
Good Practice ◽  
Mathematical Framework ◽  
Ensemble Averaging ◽  
Quality Models ◽  
Two Factors ◽  
The Common ◽  
Covariance Decomposition ◽  
Bias Variance ◽  
Model Ensembles ◽  
Operational Methods

Abstract. Ensembles of air quality models have been formally and empirically shown to outperform single models in many cases. Evidence suggests that ensemble error is reduced when the members form a diverse and accurate ensemble. Diversity and accuracy are hence two factors that should be taken care of while designing ensembles in order for them to provide better predictions. There exists a trade-off between diversity and accuracy for which one cannot be gained without expenses of the other. Theoretical aspects like the bias-variance-covariance decomposition and the accuracy-diversity decomposition are linked together and support the importance of creating ensemble that incorporates both the elements. Hence, the common practice of unconditional averaging of models without prior manipulation limits the advantages of ensemble averaging. We demonstrate the importance of ensemble accuracy and diversity through an inter-comparison of ensemble products for which a sound mathematical framework exists, and provide specific recommendations for model selection and weighting for multi model ensembles. To this end we have devised statistical tools that can be used for diagnostic evaluation of ensemble modelling products, complementing existing operational methods.

Sign in / Sign up

Export Citation Format

Share Document