Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

ICML
2010
IEEE

favoriteEmaildiscussreport

230views Machine Learning» more ICML 2010»

Multi-Task Learning of Gaussian Graphical Models

13 years 5 months ago

Multi-Task Learning of Gaussian Graphical Models

Download www.cs.sunysb.edu

We present multi-task structure learning for Gaussian graphical models. We discuss uniqueness and boundedness of the optimal solution of the maximization problem. A block coordinate descent method leads to a provably convergent algorithm that generates a sequence of positive definite solutions. Thus, we reduce the original problem into a sequence of strictly convex regularized quadratic minimization subproblems. We further show that this subproblem leads to the continuous quadratic knapsack problem, for which very efficient methods exist. Finally, we show promising results in a dataset that captures brain function of cocaine addicted and control subjects under conditions of monetary reward.

Jean Honorio, Dimitris Samaras

Real-time Traffic

ICML 2010 | Machine Learning | Maximization Problem | Quadratic Knapsack Problem | Regularized Quadratic Minimization |

claim paper

Related Content

» MultiTask Warped Gaussian Process for Personalized Age Estimation

» Bayesian MultiTask Reinforcement Learning

» Learning Gaussian Graphical Models of Gene Networks with False Discovery Rate Control

» Sparse Gaussian graphical models with unknown block structure

» Convex optimization techniques for fitting sparse Gaussian graphical models

» Learning Gaussian tree models analysis of error exponents and extremal structures

» Learning the Structure of Deep Sparse Graphical Models

» Gaussian multiresolution models exploiting sparse Markov and covariance structure

» Expandable DataDriven Graphical Modeling of Human Actions Based on Salient Postures

Post Info
More Details (n/a)

Added	09 Nov 2010
Updated	09 Nov 2010
Type	Conference
Year	2010
Where	ICML
Authors	Jean Honorio, Dimitris Samaras

Comments (0)