Corpus ID: 127008

# Graph-based Generalization Bounds for Learning Binary Relations

@article{London2013GraphbasedGB,
title={Graph-based Generalization Bounds for Learning Binary Relations},
author={Ben London and Bert Huang and L. Getoor},
journal={ArXiv},
year={2013},
volume={abs/1302.5348}
}
• Published 2013
• Mathematics, Computer Science
• ArXiv
We investigate the generalizability of learned binary relations: functions that map pairs of instances to a logical indicator. This problem has application in numerous areas of machine learning, such as ranking, entity resolution and link prediction. Our learning framework incorporates an example labeler that, given a sequence $X$ of $n$ instances and a desired training size $m$, subsamples $m$ pairs from $X \times X$ without replacement. The challenge in analyzing this learning scenario is… Expand
3 Citations

#### References

SHOWING 1-10 OF 20 REFERENCES
Learning Binary Relations and Total Orders
• Mathematics, Computer Science
• SIAM J. Comput.
• 1993
Generalization Bounds for Ranking Algorithms via Algorithmic Stability
• Mathematics, Computer Science
• J. Mach. Learn. Res.
• 2009
Chromatic PAC-Bayes Bounds for Non-IID Data
• Computer Science, Mathematics
• AISTATS
• 2009
Rademacher Complexity Bounds for Non-I.I.D. Processes
• Computer Science, Mathematics
• NIPS
• 2008
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
• Mathematics, Computer Science
• J. Mach. Learn. Res.
• 2001