Tight Bounds on Approximation and Learning of Self-Bounding Functions

We study the complexity of learning and approximation of self-bounding functions over the uniform distribution on the Boolean hypercube . Informally, a function is self-bounding if for every , upper bounds the sum of all the marginal decreases in the value of the function at . Self-bounding functions include such well-known classes of functions as submodular and fractionally-subadditive (XOS) functions. They were introduced by Boucheron et al. (2000) in the context of concentration of measure inequalities. Our main result is a nearly tight -approximation of self-bounding functions by low-degree juntas. Specifically, all self-bounding functions can be -approximated in by a polynomial of degree over variables. We show that both the degree and junta-size are optimal up to logarithmic terms. Previous techniques considered stronger approximation and proved nearly tight bounds of on the degree and on the number of variables. Our bounds rely on the analysis of noise stability of self-bounding functions together with a stronger connection between noise stability and approximation by low-degree polynomials. This technique can also be used to get tighter bounds on approximation by low-degree polynomials and faster learning algorithm for halfspaces. These results lead to improved and in several cases almost tight bounds for PAC and agnostic learning of self-bounding functions relative to the uniform distribution. In particular, assuming hardness of learning juntas, we show that PAC and agnostic learning of self-bounding functions have complexity of .
View on arXiv