On selecting the largest element in spite of erroneous information
4th Annual Symposium on Theoretical Aspects of Computer Sciences on STACS 87
Computing with unreliable information
STOC '90 Proceedings of the twenty-second annual ACM symposium on Theory of computing
Searching in the presence of linearly bounded errors
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
Comparison-based search in the presence of errors
STOC '93 Proceedings of the twenty-fifth annual ACM symposium on Theory of computing
Classification by pairwise coupling
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Multiclass learning, boosting, and error-correcting codes
COLT '99 Proceedings of the twelfth annual conference on Computational learning theory
Selection in the presence of noise: the design of playoff systems
SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms
Reliable minimum finding comparator networks
Fundamenta Informaticae
Reducing multiclass to binary: a unifying approach for margin classifiers
The Journal of Machine Learning Research
Cost-Sensitive Learning by Cost-Proportionate Example Weighting
ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
Solving multiclass learning problems via error-correcting output codes
Journal of Artificial Intelligence Research
Sensitive error correcting output codes
COLT'05 Proceedings of the 18th annual conference on Learning Theory
A hierarchical classifier applied to multi-way sentiment detection
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Reducing position-sensitive subset ranking to classification
Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in artificial intelligence
Generic subset ranking using binary classifiers
Theoretical Computer Science
Efficient discriminative learning of class hierarchy for many class prediction
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
A theory of multiclass boosting
The Journal of Machine Learning Research
| Hi-index | 0.00 |
We present a family of pairwise tournaments reducing k-class classification to binary classification. These reductions are provably robust against a constant fraction of binary errors, and match the best possible computation and regret up to a constant.