Communications of the ACM
How to construct random functions
Journal of the ACM (JACM)
Learning decision trees using the Fourier spectrum
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
Learning k-term DNF formulas with an incomplete membership oracle
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Exact identification of read-once formulas using fixed points of amplification functions
SIAM Journal on Computing
Cryptographic primitives based on hard learning problems
CRYPTO '93 Proceedings of the 13th annual international cryptology conference on Advances in cryptology
Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle
Machine Learning - Special issue on computational learning theory
Algorithmic complexity in coding theory and the minimum distance problem
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Malicious Omissions and Errors in Answers to Membership Queries
Machine Learning
Efficient noise-tolerant learning from statistical queries
Journal of the ACM (JACM)
Noise-tolerant learning, the parity problem, and the statistical query model
STOC '00 Proceedings of the thirty-second annual ACM symposium on Theory of computing
Machine Learning
Machine Learning
A Note on Learning DNF Formulas Using Equivalence and Incomplete Membership Queries
AII '94 Proceedings of the 4th International Workshop on Analogical and Inductive Inference: Algorithmic Learning Theory
Learning Regular Sets with an Incomplete Membership Oracle
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Learning with Queries Corrupted by Classification Noise
ISTCS '97 Proceedings of the Fifth Israel Symposium on the Theory of Computing Systems (ISTCS '97)
Learning monotone dnf from a teacher that almost does not answer membership queries
The Journal of Machine Learning Research
On lattices, learning with errors, random linear codes, and cryptography
Proceedings of the thirty-seventh annual ACM symposium on Theory of computing
New Results for Learning Noisy Parities and Halfspaces
FOCS '06 Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science
Attribute-Efficient and Non-adaptive Learning of Parities and DNF Expressions
The Journal of Machine Learning Research
Hi-index | 0.00 |
We study the power of two models of faulty teachers in Angluin's exact learning model. The first model we consider is learning from equivalence and incomplete membership query oracles introduced by Angluin and Slonim [1]. In this model, the answers to a random subset of the learner's membership queries may be missing. The second model we consider is random persistent classification noise in membership queries introduced by Goldman et al. [2]. In this model, the answers to a random subset of the learner's membership queries are flipped.We show that the incomplete membership query oracle is strictly stronger than the membership query oracle with persistent noise under the assumption that the problem of PAC learning parities with noise is intractable.We also show that under the standard cryptographic assumptions the incomplete membership query oracle is strictly weaker than the perfect membership query oracle. This strengthens the result of Simon [3] and resolves an open question of Bshouty and Eiron [4].Our techniques are based on ideas from coding theory and cryptography.