Learning Convex Bodies under Uniform Distribution
نویسنده
چکیده
Kern, W.. Learning convex bodies under uniform distribution. Information Processing Letters 43 (lY92) 35-3’). We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.
منابع مشابه
A generalization of Lehmann’s Theorem on the comparison of uniform location experiments
We generalize a result of Lehmann on the comparison of location experiments with uniform distributions on intervals. We compare in this paper a location experiment consisting of uniform distributions on parallelepipeds with a location experiment consisting of uniform distributions on convex bodies. We show that the first experiment can only be more informative than the second one if the convex ...
متن کاملTesting Convexity of Figures Under the Uniform Distribution
We consider the following basic geometric problem: Given ∈ (0, 1/2), a 2-dimensional figure that consists of a black object and a white background is -far from convex if it differs in at least an fraction of the area from every figure where the black object is convex. How many uniform and independent samples from a figure that is -far from convex are needed to detect a violation of convexity wi...
متن کاملNo return to convexity
In the paper we study closures of classes of log–concave measures under taking weak limits, linear transformations and tensor products. We consider what uniform measures on convex bodies can one obtain starting from some class K. In particular we prove that if one starts from one–dimensional log–concave measures, one obtains no non– trivial uniform mesures on convex bodies.
متن کاملRisk of Sequential Estimator of the Failure Rate of Exponential Distribution under Convex Boundary
In this paper the exact determination of the distribution of stopping variable, the moment and risk of sequential estimator of the failure rate of exponential distribution, under convex boundary is obtained. The corresponding Poisson Process is used to derive the exact distribution of stopping variable of sequential estimator of the failure rate. In the end the exact values of mean and risk ...
متن کاملDistribution of Mass in Convex Bodies
The main topic of this thesis is the distribution of mass of convex bodies in finite dimensional Euclidean space. We are interested in phenomena which occur in high dimensions, and mainly investigate the dependence of several geometric quantitative properties on the dimension. We consider the uniform measure on a convex body and establish connections between quantities such as covariance, entro...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Inf. Process. Lett.
دوره 43 شماره
صفحات -
تاریخ انتشار 1992