STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
SODA '09 Proceedings of the twentieth Annual ACM-SIAM Symposium on Discrete Algorithms
SIAM Journal on Computing
Testing (subclasses of) halfspaces
Property testing
Testing (subclasses of) halfspaces
Property testing
SIAM Journal on Computing
Nearly optimal solutions for the chow parameters problem and low-weight approximation of halfspaces
STOC '12 Proceedings of the forty-fourth annual ACM symposium on Theory of computing
The inverse shapley value problem
ICALP'12 Proceedings of the 39th international colloquium conference on Automata, Languages, and Programming - Volume Part I
Improved Approximation of Linear Threshold Functions
Computational Complexity
Hi-index | 0.00 |
A Boolean perceptron is a linear threshold function over the discrete Boolean domain {0,1}n. That is, it maps any binary vector to 0 or 1, depending on whether the vector's components satisfy some linear inequality. In 1961, Chow showed that any Boolean perceptron is determined by the average or "center of gravity" of its "true" vectors (those that are mapped to 1), together with the total number of true vectors. Moreover, these quantities distinguish the function from any other Boolean function, not just from other Boolean perceptrons.In this paper we go further, by identifying a lower bound on the Euclidean distance between the average satisfying assignment of a Boolean perceptron and the average satisfying assignment of a Boolean function that disagrees with that Boolean perceptron on a fraction $\epsilon$ of the input vectors. The distance between the two means is shown to be at least $(\epsilon/n)^{O(\log(n/\epsilon)\log(1/\epsilon))}$. This is motivated by the statistical question of whether an empirical estimate of this average allows us to recover a good approximation to the perceptron. Our result provides a mildly superpolynomial upper bound on the growth rate of the sample size required to learn Boolean perceptrons in the "restricted focus of attention" setting. In the process we also find some interesting geometrical properties of the vertices of the unit hypercube.