Corpus ID: 195345447

# Distribution-Independent PAC Learning of Halfspaces with Massart Noise

@inproceedings{Diakonikolas2019DistributionIndependentPL,
title={Distribution-Independent PAC Learning of Halfspaces with Massart Noise},
author={Ilias Diakonikolas and Themis Gouleakis and Christos Tzamos},
booktitle={NeurIPS},
year={2019}
}
• Published in NeurIPS 2019
• Computer Science, Mathematics
We study the problem of {\em distribution-independent} PAC learning of halfspaces in the presence of Massart noise. Specifically, we are given a set of labeled examples $(\mathbf{x}, y)$ drawn from a distribution $\mathcal{D}$ on $\mathbb{R}^{d+1}$ such that the marginal distribution on the unlabeled points $\mathbf{x}$ is arbitrary and the labels $y$ are generated by an unknown halfspace corrupted with Massart noise at noise rate $\eta<1/2$. The goal is to find a hypothesis $h$ that minimizes… Expand
27 Citations

#### References

SHOWING 1-10 OF 40 REFERENCES
Hardness of Learning Halfspaces with Noise
• Mathematics, Computer Science
• FOCS
• 2006
• 53
Efficient Learning of Linear Separators under Bounded Noise
• Computer Science, Mathematics
• COLT
• 2015
• 54
• PDF
Learning geometric concepts with nasty noise
• Computer Science, Mathematics
• STOC
• 2018
• 51
• PDF
Learning Halfspaces with Malicious Noise
• Mathematics, Computer Science
• ICALP
• 2009
• 92
• PDF
Efficient Algorithms for Outlier-Robust Regression
• Computer Science, Mathematics
• COLT
• 2018
• 79
• PDF