Learning DNF over the uniform distribution using a quantum example oracle

Abstract : We generalize the notion of PAC learning from an example oracle to a notion of efficient learning on a quantum computer using a quantum example oracle. This quantum example oracle is a natural extension of the traditional PAC example oracle, and it immediately follows that all PAC-learnable function classes are learnable in the quantum model. Furthermore, we obtain positive quantum learning results for classes that are not known to be PAC learnable. Specifically, we show that DNF is efficiently learnable with respect to the uniform distribution by a quantum algorithm using a quantum example oracle. While it was already known that DNF is uniform-learnable using a membership oracle, the quantum example oracle is provably less powerful than a membership oracle. We also generalize the notion of classification noise to the quantum setting and show that the quantum DNF algorithm learns even in the presence of such noise. This result contrasts with a recent negative result for DNF in the statistical query model of learning from noisy data. Quantum computation, Computational learning theory DNF, (Disjunctive normal form), Quantum example oracle, Classification noise, Statistical query learning

[1]  Richard J. Lipton,et al.  Proceedings of the tenth annual ACM symposium on Theory of computing , 1978 .

[2]  Thomas R. Hancock,et al.  Learning 2µ DNF Formulas and kµ Decision Trees , 1991, COLT.

[3]  Yoav Freund,et al.  An improved boosting algorithm and its implications on learning complexity , 1992, COLT '92.

[4]  Umesh V. Vazirani,et al.  Quantum complexity theory , 1993, STOC.

[5]  Jehoshua Bruck,et al.  Harmonic Analysis of Polynomial Threshold Functions , 1990, SIAM J. Discret. Math..

[6]  Leslie G. Valiant,et al.  On the learnability of Boolean formulae , 1987, STOC.

[7]  Eyal Kushilevitz,et al.  Learning Decision Trees Using the Fourier Spectrum , 1993, SIAM J. Comput..

[8]  Eli Shamir,et al.  Learning with queries corrupted by classification noise , 1997, Proceedings of the Fifth Israeli Symposium on Theory of Computing and Systems.

[9]  Jeffrey C. Jackson,et al.  An efficient membership-query algorithm for learning DNF with respect to the uniform distribution , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[10]  Lisa Hellerstein,et al.  Read-thrice DNF is hard to learn with membership and equivalence queries , 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

[11]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[12]  Nader H. Bshouty,et al.  Exact learning via the Monotone theory , 1993, Proceedings of 1993 IEEE 34th Annual Foundations of Computer Science.

[13]  Eyal Kushilevitz,et al.  On learning Read-k-Satisfy-j DNF , 1994, COLT '94.

[14]  Avrim Blum,et al.  Fast learning of k-term DNF formulas with queries , 1992, STOC '92.

[15]  Yishay Mansour,et al.  Weakly learning DNF and characterizing statistical query learning using Fourier analysis , 1994, STOC '94.

[16]  Leonid A. Levin,et al.  A hard-core predicate for all one-way functions , 1989, STOC '89.

[17]  Leonard Pitt,et al.  Exact learning of read-k disjoint DNF and not-so-disjoint DNF , 1992, COLT '92.

[18]  Andrew Chi-Chih Yao,et al.  Quantum Circuit Complexity , 1993, FOCS.

[19]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[20]  H. S. Allen.  The Quantum Theory , 1928, Nature.

[21]  Eyal Kushilevitz,et al.  On learning visual concepts and DNF formulae , 1993, COLT '93.

[22]  G. Brassard,et al.  Oracle Quantum Computing , 1992, Workshop on Physics and Computation.

[23]  Gilles Brassard,et al.  The quantum challenge to structural complexity theory , 1992, [1992] Proceedings of the Seventh Annual Structure in Complexity Theory Conference.

[24]  Daniel R. Simon,et al.  On the power of quantum computation , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[25]  D. Deutsch,et al.  Rapid solution of problems by quantum computation , 1992, Proceedings of the Royal Society of London. Series A: Mathematical and Physical Sciences.

[26]  Noam Nisan,et al.  Constant depth circuits, Fourier transform, and learnability , 1989, 30th Annual Symposium on Foundations of Computer Science.

[27]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[28]  Peter W. Shor,et al.  Algorithms for quantum computation: discrete logarithms and factoring , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[29]  Thomas R. Hancock,et al.  Learning 2u DNF formulas and ku decision trees , 1991, COLT 1991.

[30]  H. Aizenstein,et al.  Exact learning of read-twice DNF formulas , 1991, [1991] Proceedings 32nd Annual Symposium of Foundations of Computer Science.

[31]  Yoav Freund,et al.  Boosting a weak learning algorithm by majority , 1995, COLT '90.

[32]  D. Deutsch.  Quantum theory, the Church–Turing principle and the universal quantum computer , 1985, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[33]  Noam Nisan,et al.  Constant depth circuits, Fourier transform, and learnability , 1993, JACM.

[34]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[35]  Dana Angluin,et al.  When won't membership queries help? , 1991, STOC '91.

[36]  J. C. Jackson.  The harmonic sieve: a novel application of Fourier analysis to machine learning theory and practice , 1996 .