Poster
Boosted Density Estimation Remastered
Zac Cranko · Richard Nock

Tue Jun 11th 06:30 -- 09:00 PM @ Pacific Ballroom #161
There has recently been a steady increase in the number iterative
approaches to density estimation. However, an accompanying burst
of formal convergence guarantees has not followed; all results pay
the price of heavy assumptions which are often unrealistic or hard
to check. The \emph{Generative Adversarial Network (GAN)}
literature --- seemingly orthogonal to the aforementioned pursuit
--- has had the side effect of a renewed interest in variational
divergence minimisation (notably $f$-GAN). We show how to combine
this latter approach and the classical boosting theory in supervised
learning to get the first density estimation algorithm that provably
achieves geometric convergence under very weak assumptions. We do so by a trick allowing to combine
\textit{classifiers} as the sufficient statistics of an
exponential family. Our analysis includes an improved variational characterisation of $f$-GAN.