Quantum Algorithms for Learning and Testing Juntas

Details Quantum Algorithms for Learning and Testing Juntas Quantum Algorithms for Learning and Testing Juntas

2007-07-24

arxiv.org/abs/0707.3479v1

Quantum Information Processing, Vol. 6, No. 5, 323 - 348 (2007)

Physics

Quantum Physics

15 pages, 1 figure. Uses synttree package. To appear in Quantum Information Processing

Scientific paper

10.1007/s11128-007-0061-6

In this article we develop quantum algorithms for learning and testing juntas, i.e. Boolean functions which depend only on an unknown set of k out of n input variables. Our aim is to develop efficient algorithms: - whose sample complexity has no dependence on n, the dimension of the domain the Boolean functions are defined over; - with no access to any classical or quantum membership ("black-box") queries. Instead, our algorithms use only classical examples generated uniformly at random and fixed quantum superpositions of such classical examples; - which require only a few quantum examples but possibly many classical random examples (which are considered quite "cheap" relative to quantum examples). Our quantum algorithms are based on a subroutine FS which enables sampling according to the Fourier spectrum of f; the FS subroutine was used in earlier work of Bshouty and Jackson on quantum learning. Our results are as follows: - We give an algorithm for testing k-juntas to accuracy $\epsilon$ that uses $O(k/\epsilon)$ quantum examples. This improves on the number of examples used by the best known classical algorithm. - We establish the following lower bound: any FS-based k-junta testing algorithm requires $\Omega(\sqrt{k})$ queries. - We give an algorithm for learning $k$-juntas to accuracy $\epsilon$ that uses $O(\epsilon^{-1} k\log k)$ quantum examples and $O(2^k \log(1/\epsilon))$ random examples. We show that this learning algorithms is close to optimal by giving a related lower bound.

Affiliated with

Also associated with

No associations

Rating

Quantum Algorithms for Learning and Testing Juntas does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Quantum Algorithms for Learning and Testing Juntas, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Quantum Algorithms for Learning and Testing Juntas will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-439987