Corpus ID: 8441637

Robust Interactive Learning

@inproceedings{Balcan2012RobustIL,
  title={Robust Interactive Learning},
  author={Maria-Florina Balcan and Steve Hanneke},
  booktitle={COLT},
  year={2012}
}
  • Maria-Florina Balcan, Steve Hanneke
  • Published in COLT 2012
  • Computer Science, Mathematics
  • In this paper we propose and study a generalization of the standard active-learning model where a more general type of query, class conditional query, is allowed. Such queries have been quite useful in applications, but have been lacking theoretical understanding. In this work, we characterize the power of such queries under two well-known noise models. We give nearly tight upper and lower bounds on the number of queries needed to learn both for the general agnostic setting and for the bounded… CONTINUE READING
    40 Citations
    Bounded Memory Active Learning through Enriched Queries
    • PDF
    Interactive Linear Regression with Pairwise Comparisons
    • 1
    Noise-Tolerant Interactive Learning Using Pairwise Comparisons
    • 19
    • PDF
    Distributed Learning, Communication Complexity and Privacy
    • 159
    • PDF
    Minimax Analysis of Active Learning
    • 48
    • PDF
    Active Classification with Comparison Queries
    • 37
    • Highly Influenced
    • PDF
    Active Learning from Imperfect Labelers
    • 28
    • PDF
    Search Improves Label for Active Learning
    • 19
    • Highly Influenced
    • PDF
    L G ] 2 4 O ct 2 01 6 Search Improves Label for Active Learning
    • 1
    • Highly Influenced

    References

    SHOWING 1-10 OF 43 REFERENCES
    A General Dimension for Exact Learning
    • 18
    A General Agnostic Active Learning Algorithm
    • 261
    • PDF
    Queries and Concept Learning
    • 623
    • PDF
    Agnostic active learning
    • 377
    • PDF
    The true sample complexity of active learning
    • 157
    • PDF
    Teaching Dimension and the Complexity of Active Learning
    • 76
    A New Abstract Combinatorial Dimension for Exact Learning via Queries
    • 17
    • PDF
    Analysis of Perceptron-Based Active Learning
    • 132
    • PDF
    A bound on the label complexity of agnostic active learning
    • 245
    • PDF
    Active Learning in the Non-realizable Case
    • 119