Corpus ID: 229297956

Hardness of Learning Halfspaces with Massart Noise

  title={Hardness of Learning Halfspaces with Massart Noise},
  author={Ilias Diakonikolas and D. Kane},
  • Ilias Diakonikolas, D. Kane
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • We study the complexity of PAC learning halfspaces in the presence of Massart (bounded) noise. Specifically, given labeled examples $(x, y)$ from a distribution $D$ on $\mathbb{R}^{n} \times \{ \pm 1\}$ such that the marginal distribution on $x$ is arbitrary and the labels are generated by an unknown halfspace corrupted with Massart noise at rate $\eta<1/2$, we want to compute a hypothesis with small misclassification error. Characterizing the efficient learnability of halfspaces in the Massart… CONTINUE READING
    2 Citations
    Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise
    • PDF
    Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
    • PDF


    Efficient active learning of sparse halfspaces with arbitrary bounded noise
    • 10
    • PDF
    Learning Halfspaces with Tsybakov Noise
    • 6
    • PDF
    Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces
    • 27
    • PDF
    Complexity theoretic limitations on learning halfspaces
    • 88
    • PDF
    Hardness of Learning Halfspaces with Noise
    • V. Guruswami, P. Raghavendra
    • Mathematics, Computer Science
    • 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06)
    • 2006
    • 76
    • PDF