### Abstract

A nonsingular transformation of binary-valued random vectors y equals xA which minimizes a mutual information criterion I(y) is considered. It is shown that a nonsingular A exists such that I(y) equals 0 if and only if x has a generalized binomial distribution. Computational algorithms for seeking an optimal A are developed, and dimensionality reduction is discussed briefly. This linear transformation is useful in improving the approximation of probability distributions. Numerical examples are presented.

Original language | English |
---|---|

Pages (from-to) | 152-156 |

Number of pages | 5 |

Journal | IEEE Transactions on Information Theory |

Volume | IT-24 |

Issue number | 2 |

State | Published - Mar 1 1978 |

### Fingerprint

### ASJC Scopus subject areas

- Information Systems
- Electrical and Electronic Engineering

### Cite this

*IEEE Transactions on Information Theory*,

*IT-24*(2), 152-156.

**LINEAR TRANSFORMATION OF BINARY RANDOM VECTORS AND ITS APPLICATION TO APPROXIMATING PROBABILITY DISTRIBUTIONS.** / Young, Tzay Y.; Liu, Philip S.

Research output: Contribution to journal › Article

*IEEE Transactions on Information Theory*, vol. IT-24, no. 2, pp. 152-156.

}

TY - JOUR

T1 - LINEAR TRANSFORMATION OF BINARY RANDOM VECTORS AND ITS APPLICATION TO APPROXIMATING PROBABILITY DISTRIBUTIONS.

AU - Young, Tzay Y.

AU - Liu, Philip S.

PY - 1978/3/1

Y1 - 1978/3/1

N2 - A nonsingular transformation of binary-valued random vectors y equals xA which minimizes a mutual information criterion I(y) is considered. It is shown that a nonsingular A exists such that I(y) equals 0 if and only if x has a generalized binomial distribution. Computational algorithms for seeking an optimal A are developed, and dimensionality reduction is discussed briefly. This linear transformation is useful in improving the approximation of probability distributions. Numerical examples are presented.

AB - A nonsingular transformation of binary-valued random vectors y equals xA which minimizes a mutual information criterion I(y) is considered. It is shown that a nonsingular A exists such that I(y) equals 0 if and only if x has a generalized binomial distribution. Computational algorithms for seeking an optimal A are developed, and dimensionality reduction is discussed briefly. This linear transformation is useful in improving the approximation of probability distributions. Numerical examples are presented.

UR - http://www.scopus.com/inward/record.url?scp=0017946770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0017946770&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0017946770

VL - IT-24

SP - 152

EP - 156

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

SN - 0018-9448

IS - 2

ER -