TY - GEN
T1 - Generalization bounds for domain adaptation
AU - Zhang, Chao
AU - Zhang, Lei
AU - Ye, Jieping
N1 - Funding Information:
Manuscript received August 19, 2008; revised April 7, 2009. First published June 26, 2009; current version published September 16, 2009. The work of Y. Li and Z. Yu was supported by the National Natural Science Foundation of China under Grant 60825306 and Grant 60802068. Asterisk indicates corresponding author.
PY - 2012
Y1 - 2012
N2 - In this paper, we provide a new framework to study the generalization bound of the learning process for domain adaptation. We consider two kinds of representative domain adaptation settings: one is domain adaptation with multiple sources and the other is domain adaptation combining source and target data. In particular, we use the integral probability metric to measure the difference between two domains. Then, we develop the specific Hoeffding-type deviation inequality and symmetrization inequality for either kind of domain adaptation to achieve the corresponding generalization bound based on the uniform entropy number. By using the resultant generalization bound, we analyze the asymptotic convergence and the rate of convergence of the learning process for domain adaptation. Meanwhile, we discuss the factors that affect the asymptotic behavior of the learning process. The numerical experiments support our results.
AB - In this paper, we provide a new framework to study the generalization bound of the learning process for domain adaptation. We consider two kinds of representative domain adaptation settings: one is domain adaptation with multiple sources and the other is domain adaptation combining source and target data. In particular, we use the integral probability metric to measure the difference between two domains. Then, we develop the specific Hoeffding-type deviation inequality and symmetrization inequality for either kind of domain adaptation to achieve the corresponding generalization bound based on the uniform entropy number. By using the resultant generalization bound, we analyze the asymptotic convergence and the rate of convergence of the learning process for domain adaptation. Meanwhile, we discuss the factors that affect the asymptotic behavior of the learning process. The numerical experiments support our results.
UR - http://www.scopus.com/inward/record.url?scp=84877734812&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84877734812&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84877734812
SN - 9781627480031
T3 - Advances in Neural Information Processing Systems
SP - 3320
EP - 3328
BT - Advances in Neural Information Processing Systems 25
T2 - 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Y2 - 3 December 2012 through 6 December 2012
ER -