TY - JOUR
T1 - Row and column generation algorithms for minimum margin maximization of ranking problems
AU - Izunaga, Yoichi
AU - Sato, Keisuke
AU - Tatsumi, Keiji
AU - Yamamoto, Yoshitsugu
N1 - Publisher Copyright:
© 2015 The Operations Research Society of Japan.
PY - 2015
Y1 - 2015
N2 - We consider the ranking problem of learning a ranking function from the data set of objects each of which is endowed with an attribute vector and a ranking label chosen from the ordered set of labels. We propose two different formulations: primal problem, primal problem with dual representation of normal vector, and then propose to apply the kernel technique to the latter formulation. We also propose algorithms based on the row and column generation in order to mitigate the computational burden due to the large number of objects.
AB - We consider the ranking problem of learning a ranking function from the data set of objects each of which is endowed with an attribute vector and a ranking label chosen from the ordered set of labels. We propose two different formulations: primal problem, primal problem with dual representation of normal vector, and then propose to apply the kernel technique to the latter formulation. We also propose algorithms based on the row and column generation in order to mitigate the computational burden due to the large number of objects.
UR - http://www.scopus.com/inward/record.url?scp=84958953253&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84958953253&partnerID=8YFLogxK
U2 - 10.15807/jorsj.58.394
DO - 10.15807/jorsj.58.394
M3 - Article
AN - SCOPUS:84958953253
SN - 0453-4514
VL - 58
SP - 394
EP - 409
JO - Journal of the Operations Research Society of Japan
JF - Journal of the Operations Research Society of Japan
IS - 4
ER -