Is there a formal treatment of the role/power of latent/hidden variables in graphical models and other machine learning models (e.g., structural equation models)?

For example, the Restricted Boltzman Machine is a graphical model which is a compact representation of a probability distribution of $x$, but it is modeled as a joint distribution with a hidden variable $h$ (i.e., we model $p(x,h)$ instead of $p(x)$). Why is $p(x,h)$ any more powerful than a suitable representation for $p(x)$?


1 Answer 1


Hidden variables simplify the description of certain models. They do not give any more modelling power. For any model with hidden variables, there is an equivalent model without them.

  • $\begingroup$ Thanks. I figured out and also saw the same in this webpage: cs.ubc.ca/~murphyk/Bayes/bnintro.html (under the title "Inventing new hidden nodes"). Now I understand hidden variables lower model complexity. $\endgroup$
    – Vimal
    Sep 22, 2014 at 0:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.