Abstract
In this paper, we study the following variant of the junta learning problem. We are given oracle access to a Boolean function f on n variables that only depends on k variables, and, when restricted to them, equals some predefined function h. The task is to identify the variables the function depends on.When h is the XOR or the OR function, this gives a restricted variant of the Bernstein–Vazirani or the combinatorial group testing problem, respectively.
We analyze the general case using the adversary bound and give an alternative formulation for the quantum query complexity of this problem. We construct optimal quantum query algorithms for the cases when h is the OR function (complexity is \({\Theta(\sqrt{k})}\)) or the exact-half function (complexity is \({\Theta(k^{1/4})}\)). The first algorithm resolves an open problem from Ambainis & Montanaro (Quantum Inf Comput 14(5&6): 439–453, 2014). For the case when h is the majority function, we prove an upper bound of \({O(k^{1/4})}\). All these algorithms can be made exact. We obtain a quartic improvement when compared to the randomized complexity (if h is the exact-half or the majority function), and a quadratic one when compared to the non-adaptive quantum complexity (for all functions considered in the paper).
Similar content being viewed by others
References
Aaronson Scott, Shi Yaoyun (2004) Quantum Lower Bounds for the Collision and the Element Distinctness Problems. Journal of the ACM 51(4): 595–605
Ambainis Andris (2002) Quantum Lower Bounds by Quantum Arguments. Journal of Computer and System Sciences 64(4): 750–767
Andris Ambainis, Kazuo Iwama, Akinori Kawachi, Hiroyuki Masuda, Raymond H Putra & Shigeru Yamashita (2004). Quantum identification of boolean oracles. In Proceedings of the 21st Symposium on Theoretical Aspects of Computer Science, volume 2996 of Lecture Notes in Computer Science, 105–116. Springer-Verlag.
Andris Ambainis & Ashley Montanaro (2014). Quantum algorithms for search with wildcards and combinatorial group testing. Quantum Information & Computation 14(5&6), 439–453.
Angluin Dana (1988) Queries and concept learning. Machine learning 2(4): 319–342
Alp Atıcı & Rocco A. Servedio (2005): Improved bounds on quantum learning algorithms. Quantum Information Processing 4(5), 355–386.
Alp Atıcı & Rocco A. Servedio (2007). Quantum algorithms for learning and testing juntas. Quantum Information Processing 6(5), 323–348.
Aleksandrs Belovs (2012a). Learning-graph-based Quantum Algorithm for k-distinctness. In Proceedings of the 53rd Annual IEEE Symposium on Foundations of Computer Science, 207–216.
Aleksandrs Belovs (2012b). Span programs for functions with constant-sized 1-certificates. In Proceedings of the 44th Annual ACM Symposium on Theory of Computing, 77–84.
Aleksandrs Belovs & Ben W. Reichardt (2012). Span programs and quantum algorithms for st-connectivity and claw detection. In Proceedings of the 20th Annual European Symposium on Algorithms, volume 7501 of Lecture Notes in Computer Science, 193–204. Springer-Verlag.
Belovs Aleksandrs., Rosmanis Ansis (2014) On the Power of Non-Adaptive Learning Graphs. Computational Complexity 23(2): 323–354
Bernstein Ethan., Vazirani Umesh (1997) Quantum complexity theory. SIAM Journal on Computing 26(5): 1411–1473
Eric Blais (2009). Testing juntas nearly optimally. In Proceedings of the 41st Annual ACM Symposium on Theory of Computing, 151–158
Stephen Boyd & Lieven Vandenberghe (2004). Convex optimization. Cambridge University Press.
Gilles Brassard, Peter Høyer, Michele Mosca & Alain Tapp (2002). Quantum amplitude amplification and estimation. In Quantum Computation and Quantum Information: A Millennium Volume, volume 305 of AMS Contemporary Mathematics Series, 53–74.
Nader H. Bshouty, Richard Cleve, Ricard Gavaldà, Sampath Kannan & Christino Tamon (1996). Oracles and queries that are sufficient for exact learning. Journal of Computer and System Sciences 52(3), 421–433.
Nader H. Bshouty & Jeffrey C. Jackson (1998). Learning DNF over the uniform distribution using a quantum example oracle. SIAM Journal on Computing 28(3) 1136–1153.
Harry Buhrman & Ronald de Wolf (2002). Complexity measures and decision tree complexity: a survey. Theoretical Computer Science 288, 21–43.
Andrew M. Childs, Richard Cleve, Enrico Deotto, Edward Farhi, Sam Gutmann & Daniel A. Spielman (2003). Exponential algorithmic speedup by a quantum walk. In Proceedings of the 35th Annual ACM Symposium on Theory of Computing, 59–68.
Andrew M. Childs, Robin Kothari, Māris Ozols & Martin Rötteler (2013). Easy and hard functions for the Boolean hidden shift problem. In Proceedings of the 8th Conference on the Theory of Quantum Computation, Communication and Cryptography, volume 22 of Leibniz International Proceedings in Informatics, 50–79. Schloss Dagstuhl.
Charles W. Curtis & Irving Reiner (1962). Representation theory of finite groups and associative algebras. American Mathematical Society.
Wim van Dam (1998). Quantum oracle interrogation: Getting all information for almost half the price. In Proceedings of the 39th Annual IEEE Symposium on Foundations of Computer Science, 362–367.
Ding Zhu Du & Frank Hwang (1993). Combinatorial group testing and its applications, volume 3 of Series on Applied Mathematics. World Scientific.
Ettinger Mark., Høyer Peter., Knill Emanuel (2004) The quantum query complexity of the hidden subgroup problem is polynomial. Information Processing Letters 91(1): 43–48
Paul Hausladen & William K. Wootters (1994). A pretty good measurement for distinguishing quantum states. Journal of Modern Optics 41(12): 2385–2390
Peter Høyer, Troy Lee, Robert Špalek (2007). Negative weights make adversaries stronger. In Proceedings of the 39th Annual ACM Symposium on Theory of Computing, 526–535
Iwama Kazuo., Nishimura Harumichi., Raymond Rudy., Teruyama Junichi (2012) Quantum counterfeit coin problems. Theoretical Computer Science 456: 51–64
Koiran Pascal., Landes Jürgen., Portier Natacha., Yao Penghui (2010) Adversary lower bounds for nonadaptive quantum algorithms. Journal of Computer and System Sciences 76(5): 347–355
Robin Kothari (2014). An optimal quantum algorithm for the oracle identification problem. In Proceedings of the 31st Symposium on Theoretical Aspects of Computer Science, volume 25 of Leibniz International Proceedings in Informatics, 482–493. Schloss Dagstuhl.
Ilia Krasikov & Simon Litsyn (2001). Survey of binary Krawtchouk polynomials. In Codes and association schemes, volume 56 of DIMACS series in Discrete Mathematics and Theoretical Computer Science, 199–212. American Mathematical Society.
Troy Lee, Frédéric Magniez & Miklos Santha (2013). Improved quantum query algorithms for triangle finding and associativity testing. In Proceedings of the 24th Annual ACM-SIAM Symposium on Discrete Algorithms, 1486–1502.
Troy Lee, Rajat Mittal, Ben W. Reichardt, Robert Špalek & Mario Szegedy (2011). Quantum query complexity of state conversion. In Proceedings of the 52nd Annual IEEE Symposium on Foundations of Computer Science, 344–353.
Montanaro Ashley (2010) Nonadaptive quantum query complexity. Information Processing Letters 110(24): 1110–1113
Ben W. Reichardt (2009). Span programs and quantum query complexity: The general adversary bound is nearly tight for every boolean function. In Proceedings of the 50th Annual IEEE Symposium on Foundations of Computer Science, 544–551.
Ben W. Reichardt & Robert Špalek (2012). Span-program-based quantum algorithm for evaluating formulas. Theory of Computing 8, 291–319.
Bruce E. Sagan (2001). The symmetric group: representations, combinatorial algorithms, and symmetric functions, volume 203 of Graduate Texts in Mathematics. Springer-Verlag.
Jean-Pierre Serre (1977). Linear Representations of Finite Groups, volume 42 of Graduate Texts in Mathematics. Springer-Verlag.
Rocco A. Servedio & Steven J Gortler (2004). Equivalences and separations between quantum and classical learnability. SIAM Journal on Computing 33(5), 1067–1092.
Robert Špalek & Mario Szegedy (2006) All Quantum Adversary Methods are Equivalent. Theory of Computing 2, 1–18
Gabor Szegő (1975). Orthogonal polynomials, volume 23 of AMS Colloquium Publications. American Mathematical Society.
Zalka Christof (1999) Grover’s quantum searching algorithm is optimal. Physical Review A 60(4): 2746
Bohua Zhan, Shelby Kimmel & Avinatan Hassidim (2012). Super-polynomial quantum speed-ups for Boolean evaluation trees with hidden structure. In Proceedings of the 3rd Innovations in Theoretical Computer Science conference, 249–265. ACM Press.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Belovs, A. Quantum Algorithms for Learning Symmetric Juntas via the Adversary Bound. comput. complex. 24, 255–293 (2015). https://doi.org/10.1007/s00037-015-0099-2
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00037-015-0099-2
Keywords
- Quantum query algorithms
- computational learning theory
- combinatorial group testing
- representation theory of the symmetric group
- semi-definite optimization