منابع مشابه
Consistency of φ-divergence errors of Barron density estimates
Our research is motivated by the need of using nonparametric density estimates foroptimization of the switching rules in the nods of telecommunication and computer networks.One of the applications in this area is to estimate tail probabilities of an unknown distribution.Thus, we need estimates as much precise as possible particularly in the tail areas. The Barronestimator, defin...
متن کاملφ φ φ φ φ φ k From Max - SAT to Min - UNSAT : Insights and Applications
This report describes a strong connection between maximum satisfiability and minimally-unsatisfiable subfor-mulas of any constraint system, as well as techniques for exploiting it. Focusing on CNF formulas, we explore this relationship and present novel algorithms for extracting minimally-unsatisfiable subformulas, including one that finds all such subformulas. We present experimental results s...
متن کاملConditional Density Approximations with Mixtures of Polynomials
Mixtures of polynomials (MoPs) are a non-parametric density estimation technique especially designed for hybrid Bayesian networks with continuous and discrete variables. Algorithms to learn oneand multi-dimensional (marginal) MoPs from data have recently been proposed. In this paper we introduce two methods for learning MoP approximations of conditional densities from data. Both approaches are ...
متن کامل1 2 Κ ′ 2 ( Φ † Φ ′ ′ ) ( Φ ′ ′
We show how the nearly bi-maximal mixing scenario comes out naturally from gauged SO(3) F flavor symmetry via spontaneous symmetry breaking. An interesting relation between the neutrino mass-squared differences and the mixing angle, i.e., ∆m 2 µe /∆m 2 τ µ ≃ 2|U e3 | 2 is obtained. The smallness of the ratio (or |U e3 |) can also naturally be understood from an approximate permutation symmetry....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Approximation Theory
سال: 1975
ISSN: 0021-9045
DOI: 10.1016/0021-9045(75)90070-2