ABSTRACT
A function on n variables is called a k-junta if it depends on at most k of its variables. In this article, we show that it is possible to test whether a function is a k-junta or is "far" from being a k-junta with O(kε + k log k ) queries, where epsilon is the approximation parameter. This result improves on the previous best upper bound of O (k3/2)ε queries and is asymptotically optimal, up to a logarithmic factor.
We obtain the improved upper bound by introducing a new algorithm with one-sided error for testing juntas. Notably, the algorithm is a valid junta tester under very general conditions: it holds for functions with arbitrary finite domains and ranges, and it holds under any product distribution over the domain.
A key component of the analysis of the new algorithm is a new structural result on juntas: roughly, we show that if a function f is "far" from being a k-junta, then f is "far" from being determined by k parts in a random partition of the variables. The structural lemma is proved using the Efron-Stein decomposition method.
- Per Austrin and Elchanan Mossel. Approximation resistant predicates from pairwise independence. In Proc. 23rd Conf. on Computational Complexity, 2008. Google ScholarDigital Library
- Mihir Bellare, Oded Goldreich, and Madhu Sudan. Free bits, PCPs and non-approximability -- towards tight results. SIAM J. Comput., 27(3):804--915, 1998. Google ScholarDigital Library
- Eric Blais. Improved bounds for testing juntas. In Proc. 12th Workshop RANDOM, pages 317--330, 2008. Google ScholarDigital Library
- Eric Blais, Ryan O'Donnell, and Karl Wimmer. Polynomial regression under arbitrary product distributions. In Proc. 21st Conf. on Learning Theory, pages 193--204, 2008.Google Scholar
- Avrim Blum, Lisa Hellerstein, and Nick Littlestone. Learning in the presence of finitely or infinitely many irrelevant attributes. J. of Comp. Syst. Sci., 50(1):32--40, 1995. Google ScholarDigital Library
- Hana Chockler and Dan Gutfreund. A lower bound for testing juntas. Information Processing Letters, 90(6):301--305, 2004. Google ScholarDigital Library
- Ilias Diakonikolas, Homin K. Lee, Kevin Matulef, Krzysztof Onak, Ronitt Rubinfeld, Rocco A. Servedio, and Andrew Wan. Testing for concise representations. In Proc. 48th Symposium on Foundations of Computer Science, pages 549--558, 2007. Google ScholarDigital Library
- Brad Efron and Charles Stein. The jackknife estimate of variance. Ann. of Stat., 9(3):586--596, 1981.Google ScholarCross Ref
- Eldar Fischer, Guy Kindler, Dana Ron, Shmuel Safra, and Alex Samorodnitsky. Testing juntas. J. Comput. Syst. Sci., 68(4):753--787, 2004. Google ScholarDigital Library
- Oded Goldreich, Shari Goldwasser, and Dana Ron. Property testing and its connection to learning and approximation. J. of the ACM, 45(4):653--750, 1998. Google ScholarDigital Library
- Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, 2001.Google Scholar
- Timothy R. Hugues et al. Expression profiling using microarrays fabricated by an ink-jet oligonucleotide synthesizer. Nature Biotechnology, 19(4):342--347, 2001.Google ScholarCross Ref
- Samuel Karlin and Yosef Rinott. Applications of ANOVA type decompositions for comparisons of conditional variance statistics including jack-knife estimates. Ann. of Statistics, 10(2):485--501, 1982.Google ScholarCross Ref
- Subhash Khot, Guy Kindler, Elchanan Mossel, and Ryan O'Donnell. Optimal inapproximability results for MAX-CUT and other two-variable CSPs? SIAM J. Comput., 37(1):319--357, 2007. Google ScholarDigital Library
- Elchanan Mossel. Gaussian bounds for noise correlation of functions and tight analysis of long codes. In Proc. 49th Symp. on Foundations of Computer Science, 2008. Google ScholarDigital Library
- Elchanan Mossel, Ryan O'Donnell, and Krzysztof Oleszkiewicz. Noise stability of functions with low influences: invariance and optimality. In Proc. 46th Symp. Foundations of Comp. Sci., pages 21--30, 2005. Google ScholarDigital Library
- Michal Parnas, Dana Ron, and Alex Samorodnitsky. Testing basic boolean formulae. SIAM J. Discret. Math., 16(1):20--46, 2003. Google ScholarDigital Library
- Ronitt Rubinfeld and Madhu Sudan. Robust characterizations of polynomials with applications to program testing. SIAM J. Comput., 25(2):252--271, 1996. Google ScholarDigital Library
- J. Michael Steele. An Efron-Stein inequality for non--symmetric statistics. Ann. of Statistics, 14(2):753--758, 1986.Google ScholarCross Ref
Index Terms
- Testing juntas nearly optimally
Recommendations
Settling the Query Complexity of Non-adaptive Junta Testing
We prove that any non-adaptive algorithm that tests whether an unknown Boolean function f:{0,1}n→ {0,1} is a k-junta or ϵ-far from every k-junta must make Ω˜(k3/2) / ϵ) many queries for a wide range of parameters k and ϵ. Our result dramatically ...
Learning juntas
STOC '03: Proceedings of the thirty-fifth annual ACM symposium on Theory of computingWe consider a fundamental problem in computational learning theory: learning an arbitrary Boolean function which depends on an unknown set of k out of n Boolean variables. We give an algorithm for learning such functions from uniform random examples ...
Testing juntas
Special issue on FOCS 2002We show that a boolean valued function over n variables, where each variable ranges in an arbitrary probability space, can be tested for the property of depending on only J of them using a number of queries that depends only polynomially on J and the ...
Comments