Corpus ID: 210701392

Noise-tolerant, Reliable Active Classification with Comparison Queries

@article{Hopkins2020NoisetolerantRA,
  title={Noise-tolerant, Reliable Active Classification with Comparison Queries},
  author={Max Hopkins and Daniel Kane and Shachar Lovett and Gaurav Mahajan},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.05497}
}
  • Max Hopkins, Daniel Kane, +1 author Gaurav Mahajan
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label in the hope of exponentially increasing efficiency. By introducing comparisons, an additional type of query comparing two points, we provide the first time… CONTINUE READING
    The Power of Comparisons for Actively Learning Linear Classifiers
    3
    Efficient active learning of sparse halfspaces with arbitrary bounded noise
    3
    Point Location and Active Learning: Learning Halfspaces Almost Optimally
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    The Power of Comparisons for Actively Learning Linear Classifiers
    3
    Active Classification with Comparison Queries
    30
    Noise-Tolerant Interactive Learning Using Pairwise Comparisons
    14
    Learning from noisy examples
    226
    Active Learning via Perfect Selective Classification
    34
    Noise-Adaptive Margin-Based Active Learning and Lower Bounds under Tsybakov Noise Condition
    15
    Minimax Analysis of Active Learning
    41
    Active and passive learning of linear separators under log-concave distributions
    91
    Efficient Learning of Linear Separators under Bounded Noise
    43
    Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
    8