Domain Adaptation with Multiple Sources

@inproceedings{Mansour2008DomainAW,
  title={Domain Adaptation with Multiple Sources},
  author={Yishay Mansour and Mehryar Mohri and Afshin Rostamizadeh},
  booktitle={NIPS},
  year={2008}
}
This paper presents a theoretical analysis of the problem of domain adaptation with multiple sources. For each source domain, the distribu tion over the input points as well as a hypothesis with error at most ǫ are given. The problem consists of combining these hypotheses to derive a hypothesis w ith small error with respect to the target domain. We present several theoretica l results relating to this problem. In particular, we prove that standard convex c ombinations of the source hypotheses… CONTINUE READING
Highly Influential
This paper has highly influenced 21 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 274 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
Showing 1-10 of 160 extracted citations

275 Citations

02040'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 275 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Statistical learning theory

View 3 Excerpts
Highly Influenced

Lea rning from multiple sources

Koby Crammer, Michael Kearns, Jennifer Wortman
In Proceedings of NIPS 2006, • 2007
View 1 Excerpt

Lea rning from Data of Variable Quality

Koby Crammer, Michael Kearns, Jennifer Wortman
In Proceedings of NIPS • 2005
View 1 Excerpt

Martı́nez. Recognizing imprecisely localize d, partially occluded, and expression variant faces from a single sample per class

M. Aleix
IEEE Trans. Pattern Anal. Mach. Intell • 2002
View 1 Excerpt

Similar Papers

Loading similar papers…