Random Variables

Janne V. Kujala, Ehtibar N. Dzhafarov

The Contextuality-by-Default approach to determining and measuring the (non)contextuality of a system of random variables requires that every random variable in the system be represented by an equivalent set of dichotomous random variables. In this paper we present general principles that justify the use of dichotomizations and determine their choice. The main idea in choosing dichotomizations is that if the set of possible values of a random variable is endowed with a pre-topology (V-space), then the allowable dichotomizations split the space of possible values into two linked subsets (“linkedness” being a weak form of pre-topological connectedness). We primarily focus on two types of random variables most often encountered in practice: categorical and real-valued ones (including continuous random variables, greatly underrepresented in the contextuality literature). A categorical variable (one with a finite number of unordered values) is represented by all of its possible dichotomizations. If the values of a random variable are real numbers, then they are dichotomized by intervals above and below a variable cut point.

Philippe Réfrégier

Roberto Piazza

Babak Hassibi, Sormeh Shadbakht

Given n (discrete or continuous) random variables Xi, the (2n- 1)-dimensional vector obtained by evaluating the joint entropy of all non-empty subsets of {X1,hellip, Xn} is called an entropic vector. Determining the region of entropic vectors is an important open problem in information theory. Recently, Chan has shown that the entropy regions for discrete and continuous random variables, though different, can be determined from one another. An important class of continuous random variables are those that are vector-valued and jointly Gaussian. It is known that Gaussian random variables violate the Ingleton bound, which many random variables such as those obtained from linear codes over finite fields do satisfy, and they also achieve certain non-Shannon inequalities. In this paper we give a full characterization of the entropy region for three jointly-Gaussian vector-valued random variables and, rather surprisingly, show that the region is strictly smaller than the entropy region for three arbitrary random variables. However, we also show the following result. For any given entropic vector h isin R7, there exists a thetas* > 0, such that for all thetas ges thetas*, the vector 1/thetas h can be generated by three vector-valued jointly Gaussian random variables. This implies that for three random variables the region of entropic vectors can be obtained by considering the cone generated by the space of Gaussian entropic vectors. It also suggests that studying Gaussian random variables for n ges 4 may be a fruitful approach to studying the space of entropic vectors for arbitrary n.

Yizhou Zhao, Hua Sun

A collection of K random variables are called (K,n)-MDS if any n of the K variables are independent and determine all remaining variables. In the MDS variable generation problem, K users wish to generate variables that are (K,n)-MDS using a randomness variable owned by each user. We show that to generate 1 bit of (K,n)-MDS variables for each n ∈ {1,2, ⋯ ,K}, the minimum size of the randomness variable at each user is 1+1/2+ ⋯ +1/K bits.

Shunlong Luo