Non-Existence of Everywhere Proper Conditional Distributions
نویسندگان
چکیده
منابع مشابه
Computing Maximum Entropy Distributions Everywhere
We study the problem of computing the maximum entropy distribution with a specified expectation over a large discrete domain. Maximum entropy distributions arise and have found numerous applications in economics, machine learning and various sub-disciplines of mathematics and computer science. The key computational questions related to maximum entropy distributions are whether they have succinc...
متن کاملOn the existence of non-central Wishart distributions
This paper deals with the existence issue of non-central Wishart distributions which is a research topic initiated by Wishart (1928), and with important contributions by e.g., Lévy (1937), Gindikin (1975), Shanbhag (1988), Peddada & Richards (1991). We present a new method involving the theory of affine Markov processes, which reveals joint necessary conditions on shape and non-centrality param...
متن کاملImproper Regular Conditional Distributions
At the bottom of page 1614, we are not precise in the definition of a Borel space. The condition should have read that there is a one-to-one measurable function with measurable inverse between (Ω,B) and (E,E), where E is a Borel subset of the reals and E is the Borel σ-field of subsets of E. After the remaining corrections below, our use of the term “Borel space” conforms with this definition. ...
متن کاملExistence and uniqueness of proper scoring rules
To discuss the existence and uniqueness of proper scoring rules one needs to extend the associated entropy functions as sublinear functions to the conic hull of the prediction set. In some natural function spaces, such as the Lebesgue L-spaces over R, the positive cones have empty interior. Entropy functions defined on such cones have directional derivatives only, which typically exist on large...
متن کامل#p-complete Conditional Distributions
We study conditional probability from the perspective of complexity theory of functions and operators in analysis, building on work by Ko (1983), Friedman (1984), and Kawamura and Cook (2010). For some random variable X in {0, 1}N whose distribution is continuous and polynomial-time computable, and some polynomial-time computable function f : {0, 1}N → [0, 1] for which the random variable f(X) ...
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: The Annals of Mathematical Statistics
سال: 1963
ISSN: 0003-4851
DOI: 10.1214/aoms/1177704259