Generalization bounds for domain adaptation

Chao Zhang, Lei Zhang, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
Pages3320-3328
Number of pages9
Volume4
StatePublished - 2012
Event26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 - Lake Tahoe, NV, United States
Duration: Dec 3 2012Dec 6 2012

Other

Other26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
CountryUnited States
CityLake Tahoe, NV
Period12/3/1212/6/12

Fingerprint

Entropy
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Zhang, C., Zhang, L., & Ye, J. (2012). Generalization bounds for domain adaptation. In Advances in Neural Information Processing Systems (Vol. 4, pp. 3320-3328)

Generalization bounds for domain adaptation. / Zhang, Chao; Zhang, Lei; Ye, Jieping.

Advances in Neural Information Processing Systems. Vol. 4 2012. p. 3320-3328.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, C, Zhang, L & Ye, J 2012, Generalization bounds for domain adaptation. in Advances in Neural Information Processing Systems. vol. 4, pp. 3320-3328, 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012, Lake Tahoe, NV, United States, 12/3/12.
Zhang C, Zhang L, Ye J. Generalization bounds for domain adaptation. In Advances in Neural Information Processing Systems. Vol. 4. 2012. p. 3320-3328
Zhang, Chao ; Zhang, Lei ; Ye, Jieping. / Generalization bounds for domain adaptation. Advances in Neural Information Processing Systems. Vol. 4 2012. pp. 3320-3328
@inproceedings{55a4148973a14c328e0e3b90f6f0fda2,
title = "Generalization bounds for domain adaptation",
abstract = "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.",
author = "Chao Zhang and Lei Zhang and Jieping Ye",
year = "2012",
language = "English (US)",
isbn = "9781627480031",
volume = "4",
pages = "3320--3328",
booktitle = "Advances in Neural Information Processing Systems",

}

TY - GEN

T1 - Generalization bounds for domain adaptation

AU - Zhang, Chao

AU - Zhang, Lei

AU - Ye, Jieping

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

VL - 4

SP - 3320

EP - 3328

BT - Advances in Neural Information Processing Systems

ER -