Baum's Algorithm Learns Intersections of Halfspaces with Respect to Log-Concave Distributions
نویسندگان
چکیده
In 1990, E. Baum gave an elegant polynomial-time algorithm for learning the intersection of two origin-centered halfspaces with respect to any symmetric distribution (i.e., any D such that D(E) = D(−E)) [3]. Here we prove that his algorithm also succeeds with respect to any mean zero distribution D with a log-concave density (a broad class of distributions that need not be symmetric). As far as we are aware, prior to this work, it was not known how to efficiently learn any class of intersections of halfspaces with respect to log-concave distributions. The key to our proof is a “Brunn-Minkowski” inequality for log-concave densities that may be of independent interest.
منابع مشابه
Learning Halfspaces with Malicious Noise
We give new algorithms for learning halfspaces in the challenging malicious noise model, where an adversary may corrupt both the labels and the underlying distribution of examples. Our algorithms can tolerate malicious noise rates exponentially larger than previous work in terms of the dependence on the dimension n, and succeed for the fairly broad class of all isotropic log-concave distributio...
متن کاملLearning Halfspaces Under Log-Concave Densities: Polynomial Approximations and Moment Matching
We give the first polynomial-time algorithm for agnostically learning any function of a constant number of halfspaces with respect to any log-concave distribution (for any constant accuracy parameter). This result was not known even for the case of PAC learning the intersection of two halfspaces. We give two very different proofs of this result. The first develops a theory of polynomial approxi...
متن کاملWeighted Polynomial Approximations: Limits for Learning and Pseudorandomness
Polynomial approximations to boolean functions have led to many positive results in computer science. In particular, polynomial approximations to the sign function underly algorithms for agnostically learning halfspaces, as well as pseudorandom generators for halfspaces. In this work, we investigate the limits of these techniques by proving inapproximability results for the sign function. First...
متن کاملSample and Computationally Efficient Learning Algorithms under S-Concave Distributions
We provide new results for noise-tolerant and sample-efficient learning algorithms under s-concavedistributions. The new class of s-concave distributions is a broad and natural generalization of log-concavity, and includes many important additional distributions, e.g., the Pareto distribution and t-distribution. This class has been studied in the context of efficient sampling, i...
متن کاملMoment-Matching Polynomials
We give a new framework for proving the existence of low-degree, polynomial approximators for Boolean functions with respect to broad classes of non-product distributions. Our proofs use techniques related to the classical moment problem and deviate significantly from known Fourier-based methods, which require the underlying distribution to have some product structure. Our main application is t...
متن کامل