Communications of the ACM
Computational limitations on learning from examples
Journal of the ACM (JACM)
Learning decision trees using the Fourier spectrum
SIAM Journal on Computing
Constant depth circuits, Fourier transform, and learnability
Journal of the ACM (JACM)
On learning monotone DNF formulae under uniform distributions
Information and Computation
Journal of the ACM (JACM)
Randomized algorithms
On the Fourier spectrum of monotone functions
Journal of the ACM (JACM)
An efficient membership-query algorithm for learning DNF with respect to the uniform distribution
Journal of Computer and System Sciences
STOC '02 Proceedings of the thiry-fourth annual ACM symposium on Theory of computing
Learning Sub-classes of Monotone DNF on the Uniform Distribution
ALT '98 Proceedings of the 9th International Conference on Algorithmic Learning Theory
On Learning Monotone Boolean Functions under the Uniform Distribution
ALT '02 Proceedings of the 13th International Conference on Algorithmic Learning Theory
On Learning Monotone Boolean Functions
FOCS '98 Proceedings of the 39th Annual Symposium on Foundations of Computer Science
On the noise sensitivity of monotone functions
Random Structures & Algorithms
Learning Random Log-Depth Decision Trees under Uniform Distribution
SIAM Journal on Computing
Learning Monotone Decision Trees in Polynomial Time
CCC '06 Proceedings of the 21st Annual IEEE Conference on Computational Complexity
The complexity of properly learning simple concept classes
Journal of Computer and System Sciences
Hardness of approximate two-level logic minimization and PAC learning with membership queries
Journal of Computer and System Sciences
Exact learning of random DNF over the uniform distribution
Proceedings of the forty-first annual ACM symposium on Theory of computing
On the learnability of shuffle ideals
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
Hi-index | 0.04 |
We give an algorithm that with high probability properly learns random monotone DNF with t(n) terms of length ~logt(n) under the uniform distribution on the Boolean cube {0,1}^n. For any function t(n)@?poly(n) the algorithm runs in time poly(n,1/@e) and with high probability outputs an @e-accurate monotone DNF hypothesis. This is the first algorithm that can learn monotone DNF of arbitrary polynomial size in a reasonable average-case model of learning from random examples only. Our approach relies on the discovery and application of new Fourier properties of monotone functions which may be of independent interest.