Quantum Algorithms for Learning Symmetric Juntas via the Adversary Bound

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 depend...

Full description

Saved in:
Bibliographic Details
Published in:Computational complexity Vol. 24; no. 2; pp. 255 - 293
Main Author: Belovs, Aleksandrs
Format: Journal Article
Language:English
Published: Basel Springer Basel 01.06.2015
Subjects:
Algorithm Analysis and Problem Complexity
Computational Mathematics and Numerical Analysis
Computer Science
Quantum query algorithms
68Q12
combinatorial group testing
semi-definite optimization
81P68
computational learning theory
representation theory of the symmetric group
ISSN:1016-3328, 1420-8954
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 Θ ( k ) ) or the exact-half function (complexity is Θ ( 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).
ISSN:1016-3328
1420-8954
DOI:10.1007/s00037-015-0099-2