Training Classifiers under Covariate Shift by Constructing the Maximum Consistent Distribution Subset

Algorithm 1

The MIDS construction algorithm.

Require: the source sample set , the target sample set , dimension ,

 size of the source sample set , size of the target sample set

Ensure: the MIDS

 ;

 Clarifying two 2-dimensional Arrays, and ;

     /The first dimension of Array records the subspace

     number of samples in the target sample set. Note that

     Array only has one record for samples with the same

     subspace number. The second dimension of Array

    records the number of samples in the corresponding subspace.

     Array is the same as , but for the source sample set/

   /obtain Array from and /

    /obtain Array from and /

    /select a maximum amount of samples from

          each subspace to compose the MIDS according

          to Array and Array /