Monotone Boolean Functions Are Universal Approximators
نویسنده
چکیده
The employment of proper codings, such as the base-2 coding, has allowed to establish the universal approximation property of Boolean functions: if a sufficient number b of inputs (bits) is taken, they are able to approximate arbitrarily well any real Borel measurable mapping. However, if the reduced set of monotone Boolean functions, whose expression involves only and and or operators, is considered, the standard approach points out significant limitations in their approximation capability. These limitations can be overcome by introducing new specific codings, called lattice coding and frame coding, which permit to show that also monotone Boolean functions possess the universal approximation property. The characteristics of these codings are analyzed in details, focusing on the ability of preserving metric and ordering. In particular, a comparison with classical base-2 coding shows that the lattice and the frame coding require an increase of O(log b) and of O( √ b), respectively, in the number of bits.
منابع مشابه
On DNF Approximators for Monotone Boolean Functions
We study the complexity of approximating monotone Boolean functions with disjunctive normal form (DNF) formulas, exploring two main directions. First, we construct DNF approximators for arbitrary monotone functions achieving one-sided error: we show that every monotone f can be ε-approximated by a DNF g of size 2n−Ωε( √ n) satisfying g(x) ≤ f(x) for all x ∈ {0, 1}. This is the first non-trivial...
متن کاملProbabilistic Construction of Monotone Formulae for Positive Linear Threshold Functions
We extend Valiant's construction of monotone formulae for the majority function to obtain an eecient probabilistic construction of small monotone formulae for arbitrary positive linear threshold functions. We show that any positive linear threshold function on n boolean variables which has weight complexity q(n) can be computed by a monotone boolean formula of size O(q(n) 3:3 n 2): Our techniqu...
متن کاملA Solution of the P versus NP Problem
Berg and Ulfberg and Amano and Maruoka have used CNF-DNF-approximators to prove exponential lower bounds for the monotone network complexity of the clique function and of Andreev's function. We show that these approximators can be used to prove the same lower bound for their non-monotone network complexity. This implies P not equal NP.
متن کاملApproximation Properties of Positive Boolean Functions
The universal approximation property is an important characteristic of models employed in the solution of machine learning problems. The possibility of approximating within a desired precision any Borel measurable function guarantees the generality of the considered approach. The properties of the class of positive Boolean functions, realizable by digital circuits containing only and and or por...
متن کاملThe Monotone Cumulants
In the present paper we define the notion of generalized cumulants which gives a universal framework for commutative, free, Boolean, and especially, monotone probability theories. The uniqueness of generalized cumulants holds for each independence, and hence, generalized cumulants are equal to the usual cumulants in commutative, free and Boolean cases. The way we define (generalized) cumulants ...
متن کامل