High-Dimensional Screening Using Multiple Grouping of Variables

Policy Search with High-Dimensional Context Variables

Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application of unsupervised dimensionality reduction methods to the context variables, suc...

High-Dimensional Structured Feature Screening Using Binary Markov Random Fields

Feature screening is a useful feature selection approach for high-dimensional data when the goal is to identify all the features relevant to the response variable. However, common feature screening methods do not take into account the correlation structure of the covariate space. We propose the concept of a feature relevance network, a binary Markov random field to represent the relevance of ea...

Syphilis screening using the multi-channel blood-grouping machine.

Variable Screening in High-dimensional Feature Space

Variable selection in high-dimensional space characterizes many contemporary problems in scientific discovery and decision making. Fan and Lv [8] introduced the concept of sure screening to reduce the dimensionality. This article first reviews the part of their ideas and results and then extends them to the likelihood based models. The techniques are then applied to disease classifications in c...

Hierarchical selection of variables in sparse high-dimensional regression

We study a regression model with a huge number of interacting variables. We consider a specific approximation of the regression function under two assumptions: (i) there exists a sparse representation of the regression function in a suggested basis, (ii) there are no interactions outside of the set of the corresponding main effects. We suggest an hierarchical randomized search procedure for sel...