Sciweavers

548 search results - page 6 / 110
» Optimization of Convex Risk Functions
Sort
View
ANOR
2010
107views more  ANOR 2010»
13 years 8 months ago
Kusuoka representation of higher order dual risk measures
We derive representations of higher order dual measures of risk in Lp spaces as suprema of integrals of Average Values at Risk with respect to probability measures on (0, 1] (Kusu...
Darinka Dentcheva, Spiridon Penev, Andrzej Ruszczy...
EMNLP
2011
12 years 10 months ago
Training a Log-Linear Parser with Loss Functions via Softmax-Margin
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Michael Auli, Adam Lopez
JGO
2008
98views more  JGO 2008»
13 years 10 months ago
Duality for almost convex optimization problems via the perturbation approach
Abstract. We deal with duality for almost convex finite dimensional optimization problems by means of the classical perturbation approach. To this aim some standard results from th...
Radu Ioan Bot, Gábor Kassay, Gert Wanka
CORR
2008
Springer
113views Education» more  CORR 2008»
13 years 10 months ago
Robustness, Risk, and Regularization in Support Vector Machines
We consider two new formulations for classification problems in the spirit of support vector machines based on robust optimization. Our formulations are designed to build in prote...
Huan Xu, Shie Mannor, Constantine Caramanis
CORR
2010
Springer
116views Education» more  CORR 2010»
13 years 11 months ago
Adaptive Bound Optimization for Online Convex Optimization
We introduce a new online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions observed so far. This is in contrast to pre...
H. Brendan McMahan, Matthew J. Streeter