Sciweavers

350 search results - page 60 / 70
» On the symmetry function of a convex set
Sort
View
COLT
1999
Springer
15 years 3 months ago
Regret Bounds for Prediction Problems
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Geoffrey J. Gordon
89
Voted
EUSFLAT
2007
107views Fuzzy Logic» more  EUSFLAT 2007»
15 years 15 days ago
Extending the Choquet integral
In decision under uncertainty, the Choquet integral yields the expectation of a random variable with respect to a fuzzy measure (or non-additive probability or capacity). In gener...
Giovanni Rossi
MP
2010
126views more  MP 2010»
14 years 9 months ago
Two row mixed-integer cuts via lifting
Recently, Andersen et al. [1], Borozan and Cornu´ejols [7] and Cornu´ejols and Margot [10] characterized extreme inequalities of a system of two rows with two free integer varia...
Santanu S. Dey, Laurence A. Wolsey
SAGA
2009
Springer
15 years 5 months ago
Bounds for Multistage Stochastic Programs Using Supervised Learning Strategies
We propose a generic method for obtaining quickly good upper bounds on the minimal value of a multistage stochastic program. The method is based on the simulation of a feasible dec...
Boris Defourny, Damien Ernst, Louis Wehenkel
KDD
2007
ACM
197views Data Mining» more  KDD 2007»
15 years 11 months ago
Learning the kernel matrix in discriminant analysis via quadratically constrained quadratic programming
The kernel function plays a central role in kernel methods. In this paper, we consider the automated learning of the kernel matrix over a convex combination of pre-specified kerne...
Jieping Ye, Shuiwang Ji, Jianhui Chen