Learning Functions of Halfspaces using Prefix Covers
نویسندگان
چکیده
We present a simple query-algorithm for learning arbitrary functions of k halfspaces under any product distribution on the Boolean hypercube. Our algorithms learn any function of k halfspaces to within accuracy ε in time O((nk/ε)) under any product distribution on {0, 1} using read-once branching programs as a hypothesis.. This gives the first poly(n, 1/ε) algorithm for learning even the intersection of 2 halfspaces under the uniform distribution on {0, 1}; previously known algorithms had an exponential dependence either on the accuracy parameter ε or the dimension n. To prove this result, we identify a new structural property of Boolean functions that yields learnability with queries: that of having a small prefix cover.
منابع مشابه
2 Learning Functions with Small Prefix
Relevant Readings: • Gopalan et al., Learning functions of halfspaces using prefix covers [GKM12].
متن کاملLearning Intersections and Thresholds of Halfspaces
We give the first polynomial time algorithm to learn any function of a constant number of halfspaces under the uniform distribution on the Boolean hypercube to within any constant error parameter. We also give the first quasipolynomial time algorithm for learning any Boolean function of a polylog number of polynomial-weight halfspaces under any distribution on the Boolean hypercube. As special ...
متن کاملImproved Lower Bounds for Learning Intersections of Halfspaces
We prove new lower bounds for learning intersections of halfspaces, one of the most important concept classes in computational learning theory. Our main result is that any statistical-query algorithm for learning the intersection of √ n halfspaces in n dimensions must make 2 √ n) queries. This is the first non-trivial lower bound on the statistical query dimension for this concept class (the pr...
متن کاملLearning, Testing, and Approximating Halfspaces
A halfspace is a Boolean function of the form f(x) = sign(w · x− θ). Halfspaces (also known as linear threshold functions, weighted majority functions, threshold gates, Perceptrons, etc.) are a natural and wellstudied class of Boolean functions. We describe recent results on approximating, testing, and learning halfspaces. In more detail, • Every halfspace can be approximated by a halfspace wit...
متن کاملLearning Intersections of Halfspaces with a Margin
We give a new algorithm for learning intersections of halfspaces with a margin, i.e. under the assumption that no example lies too close to any separating hyperplane. Our algorithm combines random projection techniques for dimensionality reduction, polynomial threshold function constructions, and kernel methods. The algorithm is fast and simple. It learns a broader class of functions and achiev...
متن کامل