We consider a composite convex minimization problem associated with regularized empirical risk minimization, which often arises in machine learning. We propose two new stochastic gradient methods that are based on stochastic dual averaging method with variance reduction. Our methods generate a sparser solution than the existing methods because we do not need to take the average of the history o...

BACKGROUND AND AIMS Research suggests that excessive online gaming may lead to symptoms commonly experienced by substance addicts. Since games are particularly appealing to children and adolescents, these individuals may be more at risk than other groups of developing gaming addiction. METHODS Given these potential concerns, a literature review was undertaken in order (i) to present the class...

This contribution extends linear models for feature vectors to sublinear models for graphs and analyzes their properties. The results are (i) a geometric interpretation of sublinear classifiers, (ii) a generic learning rule based on the principle of empirical risk minimization, (iii) a convergence theorem for the margin perceptron in the sublinearly separable case, and (iv) the VC-dimension of ...

Empirical risk minimization (ERM) is a fundamental learning rule for statistical learning problems where the data is generated according to some unknown distribution P and returns a hypothesis f chosen from a fixed class F with small loss `. In the parametric setting, depending upon (`,F ,P) ERM can have slow (1/ √ n) or fast (1/n) rates of convergence of the excess risk as a function of the sa...

DAI, Z.-J.; LIU, J.T.; LEI, Y.-P., and ZHANG, X.-L., 2010. Patterns of sediment transport pathways on a headland bay beach—Nanwan Beach, South China: a case study. Journal of Coastal Research, 26(6), 1096–1103. West Palm Beach (Florida), ISSN 0749-0208. Embayed beaches bounded by headlands, headland bay beaches, are a common feature along the coast of southern China. The patterns of sediment tr...

We have measured the transition process from the high to low resistivity states, i.e., the reset process of resistive switching based memristors based on Ni/HfO2/Sin+ structures, and have also developed an analytical model for their electrical characteristics. When the characteristic curves are plotted in the current-voltage (I-V) domain a high variability is observed. In spite of that, when th...

The electron-impact widths and shifts for six Eu ii lines and widths for three La ii, and six La iii multiplets have been calculated by using the modified semiempirical method. Estimation for Stark widths of 664.506 nm (Eu ii) and 666.634 nm (Eu iii) lines are given as well. The influence of the electron-impact mechanism on line shapes and equivalent widths in hot star atmospheres has been cons...

Answer Set Programming (ASP) is a well-known problem solving approach based on nonmonotonic logic programs and efficient solvers. HEX-programs extend ASP with external atoms for access to arbitrary external information. In this work, we extend the evaluation principles of external atoms to partial assignments, lift nogood learning to this setting, and introduce a variant of nogood minimization....

Research Online is the open access institutional repository for the University of Wollongong. For further information contact the UOW (2013). On the weighting of the mean-absolute-deviation cost minimization model. Abstract The mean-absolute-deviation cost minimization model, which aims to minimize sum of the mean value and the absolute deviation (AD) of the total cost multiplied by a given non...

An ice core extracted from Holtedahlfonna ice cap, western Spitsbergen, record spanning the period 1700–2005, was analyzed for major ions. The leading empirical orthogonal function (EOF) component is correlated with an index of summer melt (log([Na]/[Mg]) from 1850 and shows that almost 50% of the variance can be attributed to seasonal melting since the beginning of the industrial revolution. T...