VC Dimension and Learnability of Sparse Polynomials and Rational Functions
نویسندگان
چکیده
We prove upper and lower bounds on the VC dimension of sparse univariate polynomi-als over reals, and apply these results to prove uniform learnability of sparse polynomials and rational functions. As another application we solve an open problem of Vapnik ((Vap-nik 82]) on uniform approximation of the general regression functions, a central problem of computational statistics (cf. Vapnik 82]), p. 256).
منابع مشابه
Learning Real and Boolean Functions: When Is Deep Better Than Shallow
We describe computational tasks – especially in vision – that correspond to compositional/hierarchical functions. While the universal approximation property holds both for hierarchical and shallow networks, we prove that deep (hierarchical) networks can approximate the class of compositional functions with the same accuracy as shallow networks but with exponentially lower VC-dimension as well a...
متن کاملRIFIS Technical Report Complexity of Computing Generalized VC-Dimensions
In the PAC-learning model, the Vapnik-Chervonenkis (VC) dimension plays the key role to estimate the polynomial-sample learnability of a class of binary functions. For a class of multi-valued functions, the notion has been generalized in various ways. This paper investigates the complexity of computing some of generalized VC-dimensions: VC*dimension, *,-dimension, and SG-dimension. For each dim...
متن کاملLearnability of Bipartite Ranking Functions
The problem of ranking, in which the goal is to learn a real-valued ranking function that induces a ranking or ordering over an instance space, has recently gained attention in machine learning. We define a model of learnability for ranking functions in a particular setting of the ranking problem known as the bipartite ranking problem, and derive a number of results in this model. Our first mai...
متن کاملGeneralized Vandermonde Determinants over the Chebyshev Basis
It is a well known fact that the generalized Vandermonde determinant can be expressed as the product of the standard Vandermonde determinant and a polynomial with nonnegative integer coefficients. In this paper we generalize this result to Vandermonde determinants over the Chebyshev basis. We apply this result to prove that the number of real roots in [1;1] of a real polynomial is bounded by th...
متن کاملPAC Learnability of a Concept Class under Non-atomic Measures: A Problem by Vidyasagar
In response to a 1997 problem of M. Vidyasagar, we state a necessary and sufficient condition for distribution-free PAC learnability of a concept class C under the family of all non-atomic (diffuse) measures on the domain Ω. Clearly, finiteness of the classical Vapnik–Chervonenkis dimension of C is a sufficient, but no longer necessary, condition. Besides, learnability of C under non-atomic mea...
متن کامل