I'm currently reading Thomas Hofmamms paper on Probabilistic Latent Semantic Analysis.
He includes a formula for the E step in Expectation Maximisation, but has proposed an alternative to this step which looks like
$P(z;d,w) = \dfrac{[P(z)P(d|z)P(w|z)]^\beta}{\sum_{z'\in \mathcal{Z}}[P(z')P(d|z')P(w|z')]^\beta}$
I'm sure I have seen this formula in the context of something else, where it is known by a much more common name. Issue is I can't remember, and googling Tempered EM provides no useful results