Junta distance approximation with sub-exponential queries

@article{Iyer2021JuntaDA,
  title={Junta distance approximation with sub-exponential queries},
  author={Vishnu Iyer and Avishay Tal and Michael Whitmeyer},
  journal={Proceedings of the 36th Computational Complexity Conference},
  year={2021}
}
Leveraging tools of De, Mossel, and Neeman [FOCS, 2019], we show two different results pertaining to the tolerant testing of juntas. Given black-box access to a Boolean function f : {±1}n → {±1}: 1. We give a [EQUATION] query algorithm that distinguishes between functions that are γ-close to k-juntas and (γ + ε)-far from k'-juntas, where [EQUATION]. 2. In the non-relaxed setting, we extend our ideas to give a [EQUATION] (adaptive) query algorithm that distinguishes between functions that are… 

Figures from this paper

How Close is your Function to Depending on a Small Number of its Inputs?
This thesis focuses on the following question: if we have query access to some f : {− 1 , 1 } n → {− 1 , 1 } (meaning we can query any of its 2 n outputs at will), how many queries do we need to
L2-Polynomial Regression is Agnostic PAC Learner for k-Juntas
TLDR
It is proved that agnostic PAC learning of k-juntas is possible using L2 polynomial regression; hence addressing this question for k- juntas and proposing a generalization of Linial et al. (1993)’s low-degree algorithm for learning with arbitrary (non-product) distributions.
Sparsification for Sums of Exponentials and its Algorithmic Applications
TLDR
The first algorithms for approximately (and robustly) determining the number of components in a Gaussian mixture model that work without a separation condition are given.

References

SHOWING 1-10 OF 44 REFERENCES
Tolerant Junta Testing and the Connection to Submodular Optimization and Function Isomorphism
TLDR
An algorithm is designed that solves the problem of tolerant testing of k-juntas via a new polynomial-time approximation algorithm for submodular function minimization (SFM) under large cardinality constraints, which holds even when only given an approximate oracle access to the function.
Approximating the distance to monotonicity of Boolean functions
TLDR
A nonadaptive algorithm that, given oracle access to a function f, makes poly (n,1/α) queries and returns an estimate that, with high probability, is an Õ(n) ‐approximation to the distance of f to monotonicity, obtaining an analogous bound for erasure‐resilient (and tolerant) testers.
Junta Correlation is Testable
TLDR
An algorithm which given distance parameters c, d, and oracle access to a Boolean function f on the hypercube, has query complexity exp(k).poly(1/(c-d)) and distinguishes between the following cases: 1. The distance of f from any k-junta is at least c; 2. There is a k-Junta g which has distance at most d from f.
Testing juntas nearly optimally
  • Eric Blais
  • Mathematics, Computer Science
    STOC '09
  • 2009
TLDR
It is shown 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, and the structural lemma is proved using the Efron-Stein decomposition method.
Distribution-free Junta Testing
TLDR
A lower bound is shown showing that any non-adaptive distribution-free k-junta testing algorithm must make Ω(2k/3) queries even to test to accuracy ε = 1/3, and it is established that adaptivity provides an exponential improvement in the distribution- free query complexity of testing juntas.
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
Efficient Quantum Algorithms for (Gapped) Group Testing and Junta Testing
TLDR
This tester is based on a new quantum algorithm for a gapped version of the combinatorial group testing problem, with an up to quartic improvement over the query complexity of the best classical algorithm.
Improved Bounds for Testing Juntas
We consider the problem of testing functions for the property of being a k-junta (i.e., of depending on at most kvariables). Fischer, Kindler, Ron, Safra, and Samorodnitsky (J. Comput. Sys. Sci.,
Efficiently Testing Sparse GF(2) Polynomials
We give the first algorithm that is both query-efficient and time-efficient for testing whether an unknown function f:{0,1}n→{−1,1} is an s-sparse GF(2) polynomial versus ε-far from every such
Testing juntas
...
...