Learning Boxes in High Dimension 1
نویسندگان
چکیده
We present exact learning algorithms that learn several classes of (discrete) boxes in f0; : : : ; ` 1gn. In particular we learn: (1) The class of unions of O(log n) boxes in time poly(n; log `) (solving an open problem of [16, 12]; in [3] this class is shown to be learnable in time poly(n; `)). (2) The class of unions of disjoint boxes in time poly(n; t; log `), where t is the number of boxes. (Previously this was known only in the case where all boxes are disjoint in one of the dimensions; in [3] this class is shown to be learnable in time poly(n; t; `)). In particular our algorithm learns the class of decision trees over n variables, that take values in f0; : : : ; ` 1g, with comparison nodes in time poly(n; t; log `), where t is the number of leaves (this was an open problem in [9] which was shown in [4] to be learnable in time poly(n; t; `)). (3) The class of unions of O(1)-degenerate boxes (that is, boxes that depend only on O(1) variables) in time poly(n; t; log `) (generalizing the learnability of O(1)-DNF and of boxes in O(1) dimensions). The algorithm for this class uses only equivalence queries and it can also be used to learn the class of unions of O(1) boxes (from equivalence queries only).
منابع مشابه
Learning unions of high-dimensional boxes over the reals
In [4] an algorithm is presented that exactly learns (using membership queries and equivalence queries) several classes of unions of boxes in high dimension over finite discrete domains. The running time of the algorithm is polynomial in the logarithm of the size of the domain and other parameters of the target function (in particular, the dimension). We go one step further and present a PAC+MQ...
متن کاملLocal identification of scalar hybrid models with tree structure
Standard modeling approaches, for example in chemical engineering, suffer from two principal difficulties: the curse of dimension and a lack of extrapolability. We propose an approach via structured hybrid models to resolve both issues. For simplicity we consider reactor models which can be written as a tree-like composition of scalar input-output functions uj. The vertices j of the finite tree...
متن کاملA Computer Algorithm for Determining the Hausdorff Dimension of Certain Fractals
A fractal is a set which has nonintegral Hausdorff dimension. Computation of the dimension directly from the definition would be very time-consuming on a computer. However, the dimension can be computed using Newton's method if there exists a self-expanding map on the set. This technique is applied to compute the dimension of the Julia set of the quadratic mapping z —> z2 + c for small real val...
متن کاملTransparent Machine Learning Algorithm Offers Useful Prediction Method for Natural Gas Density
Machine-learning algorithms aid predictions for complex systems with multiple influencing variables. However, many neural-network related algorithms behave as black boxes in terms of revealing how the prediction of each data record is performed. This drawback limits their ability to provide detailed insights concerning the workings of the underlying system, or to relate predictions to specific ...
متن کامل