AISTATS 2022poster14 citations

Hardness of Learning a Single Neuron with Adversarial Label Noise

Ilias Diakonikolas, Daniel Kane, Pasin Manurangsi, Lisheng Ren

Abstract

We study the problem of distribution-free learning of a single neuron under adversarial label noise with respect to the squared loss. For a wide range of activation functions, including ReLUs and sigmoids, we prove hardness of learning results in the Statistical Query model and under a well-studied assumption on the complexity of refuting XOR formulas. Specifically, we establish that no polynomial-time learning algorithm, even improper, can approximate the optimal loss value within any constant factor.

BibTeX
@InProceedings{pmlr-v151-diakonikolas22a,
  title = 	 { Hardness of Learning a Single Neuron with Adversarial Label Noise },
  author =       {Diakonikolas, Ilias and Kane, Daniel and Manurangsi, Pasin and Ren, Lisheng},
  booktitle = 	 {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {8199--8213},
  year = 	 {2022},
  editor = 	 {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel},
  volume = 	 {151},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {28--30 Mar},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v151/diakonikolas22a/diakonikolas22a.pdf},
  url = 	 {https://proceedings.mlr.press/v151/diakonikolas22a.html},
  abstract = 	 { We study the problem of distribution-free learning of a single neuron under adversarial label noise with respect to the squared loss. For a wide range of activation functions, including ReLUs and sigmoids, we prove hardness of learning results in the Statistical Query model and under a well-studied assumption on the complexity of refuting XOR formulas. Specifically, we establish that no polynomial-time learning algorithm, even improper, can approximate the optimal loss value within any constant factor. }
}
Hardness of Learning a Single Neuron with Adversarial Label Noise · AISTATS 2022