Corpus ID: 211096821

# Learning Halfspaces with Massart Noise Under Structured Distributions

@article{Diakonikolas2020LearningHW,
title={Learning Halfspaces with Massart Noise Under Structured Distributions},
author={Ilias Diakonikolas and Vasilis Kontonis and Christos Tzamos and Nikos Zarifis},
journal={ArXiv},
year={2020},
volume={abs/2002.05632}
}
• Ilias Diakonikolas, +1 author Nikos Zarifis
• Published in ArXiv 2020
• Computer Science, Mathematics
• We study the problem of learning halfspaces with Massart noise in the distribution-specific PAC model. We give the first computationally efficient algorithm for this problem with respect to a broad family of distributions, including log-concave distributions. This resolves an open question posed in a number of prior works. Our approach is extremely simple: We identify a smooth {\em non-convex} surrogate loss with the property that any approximate stationary point of this loss defines a… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

#### References

##### Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

## Noise in classification

• M. F. Balcan, N. Haghtalab
• 2020

## Distribution-Independent PAC Learning of Halfspaces with Massart Noise

• Mathematics, Computer Science
• NeurIPS
• 2019

## Nonconvex sampling with the Metropolis-adjusted Langevin algorithm

• Mathematics, Computer Science
• COLT
• 2019

## The Complexity of Finding Stationary Points with Stochastic Gradient Descent

• Mathematics, Computer Science
• ArXiv
• 2019

## Noisy pac learning of halfspaces

• P. Awasthi
• TTI Chicago, Summer Workshop on Robust Statistics, available at http://www.iliasdiakonikolas.org/tti-robust/Awasthi.pdf,
• 2018

## A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics

• Mathematics, Computer Science
• COLT
• 2017

## Learning geometric concepts with nasty noise

• Mathematics, Computer Science
• STOC 2018
• 2017

## Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces

• Computer Science, Mathematics
• NIPS
• 2017

## Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions

• Computer Science
• NIPS
• 2017