Approximation with independent variables

Abstract: Given a square integrable m-dimensional random variable

X

on a probability space

(O m e g a . m a t h c a l F, P r)

and a sub sigma algebra

m a t h c a l A

, we show that there exists another m-dimensional random variable

Y

, independent of

m a t h c a l A

and minimising the

L^{2}

distance to

X

. Such results have an importance to fairness and bias reduction in Artificial Intelligence, Machine Learning and Network Theory.

Recommendations

Cites work

Cited in

(4)

This page was built for publication: Approximation with independent variables