Convexification for data fitting

Authors:
James Ting-Ho Lo
Affiliations:
Department of Mathematics and Statistics, University of Maryland Baltimore County, Baltimore, USA 21250
Venue:
Journal of Global Optimization
Year:
2010

Citing 3
Cited 2

Visual reconstruction

Visual reconstruction
State-space formulae for all stabilizing controllers that satisfy and H∞ norm bound and relations to risk sensitivity

Systems & Control Letters
On the Liu---Floudas Convexification of Smooth Programs

Journal of Global Optimization

Overcoming the local-minimum problem in training multilayer perceptrons with the NRAE training method

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I
Overcoming the local-minimum problem in training multilayer perceptrons with the NRAE-MSE training method

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.01

Visualization

Abstract

The main results reported in this paper are two theorems concerning the use of a newtype of risk-averting error criterion for data fitting. The first states that the convexity region of the risk-averting error criterion expands monotonically as its risk-sensitivity index increases. The risk-averting error criterion is easily seen to converge to the mean squared error criterion as its risk-sensitivity index goes to zero. Therefore, the risk-averting error criterion can be used to convexify the mean squared error criterion to avoid local minima. The second main theorem shows that as the risk-sensitivity index increases to infinity, the risk-averting error criterion approaches the minimax error criterion, which is widely used for robustifying system controllers and filters.