Characterizations of locally testable linear- and affine-invariant families

The linear- or affine-invariance is the property of a function family that is closed under linear- or affine-transformations on the domain, and closed under linear combinations of functions, respectively. Both the linear- and affine-invariant families of functions are generalizations of many symmetric families, for instance, the low degree polynomials. Kaufman and Sudan (2007) [21] introduced the notions of ''constraint'' and ''characterization'' to characterize the locally testable affine- and linear-invariant families of functions over finite fields of constant size. In this article, it is shown that, for any finite field F of size q and characteristic p, and its arbitrary extension field K of size Q, if an affine-invariant family @?@?{K^n->F} has a k-local constraint, then it is k^'-locally testable for k^'=k^2^Q^pQ^2^Q^p^+^4; and that if a linear-invariant family @?@?{K^n->F} has a k-local characterization, then it is k^'-locally testable for k^'=2k^2^Q^pQ^4^(^Q^p^+^1^). Consequently, for any prime field F of size q, any positive integer k, we have that for any affine-invariant family @? over field F, the four notions of ''the constraint'', ''the characterization'', ''the formal characterization'' and ''the local testability'' are equivalent modulo a poly(k,q) of the corresponding localities; and that for any linear-invariant family, the notions of ''the characterization'', ''the formal characterization'' and ''the local testability'' are equivalent modulo a poly(k,q) of the corresponding localities. The results significantly improve, and are in contrast to the characterizations in [21], which have locality exponential in Q, even if the field K is prime. In the research above, a missing result is a characterization of linear-invariant function families by the more natural notion of constraint. For this, we show that a single strong local constraint is sufficient to characterize the local testability of a linear-invariant Boolean function family, and that for any finite field F of size q greater than 2, there exists a linear-invariant function family @? over F such that it has a strong 2-local constraint, but is not q^d^q^-^1^-^1-locally testable. The proof for this result provides an appealing approach toward more negative results in the theme of characterization of locally testable algebraic properties, which is rare, and of course, significant.

[1]  Eli Ben-Sasson,et al.  Some 3CNF Properties Are Hard to Test , 2005, SIAM J. Comput..

[2]  Ronitt Rubinfeld,et al.  Robust Characterizations of Polynomials with Applications to Program Testing , 1996, SIAM J. Comput..

[3]  Ran Raz,et al.  Sub-constant error low degree test of almost-linear size , 2006, STOC '06.

[4]  Simon Litsyn,et al.  Almost orthogonal linear codes are locally testable , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[5]  Noga Alon,et al.  A combinatorial characterization of the testable graph properties: it's all about regularity , 2006, STOC '06.

[6]  Atri Rudra,et al.  Testing Low-Degree Polynomials over Prime Fields , 2004, FOCS.

[7]  Madhu Sudan,et al.  Improved Low-Degree Testing and its Applications , 2003, Comb..

[8]  László Lovász,et al.  Graph limits and parameter testing , 2006, STOC '06.

[9]  Sanjeev Arora,et al.  Probabilistic checking of proofs: a new characterization of NP , 1998, JACM.

[10]  Tadao Kasami,et al.  New generalizations of the Reed-Muller codes-I: Primitive codes , 1968, IEEE Trans. Inf. Theory.

[11]  Oded Goldreich,et al.  Locally testable codes and PCPs of almost-linear length , 2006, JACM.

[12]  Eli Ben-Sasson,et al.  Robust pcps of proximity, shorter pcps and applications to coding , 2004, STOC '04.

[13]  Avi Wigderson,et al.  Simple analysis of graph tests for linearity and PCP , 2003, Random Struct. Algorithms.

[14]  Dana Ron,et al.  Testing polynomials over general fields , 2004, 45th Annual IEEE Symposium on Foundations of Computer Science.

[15]  F. MacWilliams,et al.  The Theory of Error-Correcting Codes , 1977 .

[16]  Ronitt Rubinfeld On the Robustness of Functional Equations , 1999, SIAM J. Comput..

[17]  Dana Ron,et al.  Property testing and its connection to learning and approximation , 1998, JACM.

[18]  Luca Trevisan,et al.  Three Theorems regarding Testing Graph Properties , 2001, Electron. Colloquium Comput. Complex..

[19]  Eli Ben-Sasson,et al.  Randomness-efficient low degree tests and short PCPs via epsilon-biased sets , 2003, STOC '03.

[20]  Mihir Bellare,et al.  Linearity testing in characteristic two , 1996, IEEE Trans. Inf. Theory.

[21]  Manuel Blum,et al.  Self-testing/correcting with applications to numerical problems , 1990, STOC '90.

[22]  Kenji Obata,et al.  A lower bound for testing 3-colorability in bounded-degree graphs , 2002, The 43rd Annual IEEE Symposium on Foundations of Computer Science, 2002. Proceedings..

[23]  Noga Alon,et al.  Testing Low-Degree Polynomials over GF(2( , 2003, RANDOM-APPROX.

[24]  Madhu Sudan,et al.  2-Transitivity Is Insufficient for Local Testability , 2008, Computational Complexity Conference.

[25]  Madhu Sudan,et al.  Algebraic property testing: the role of invariance , 2008, Electron. Colloquium Comput. Complex..