Timezone: »
Poster
Boosted Density Estimation Remastered
Zac Cranko · Richard Nock
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.
Author Information
Zac Cranko (ANU)
Richard Nock (Data61, The Australian National University and the University of Sydney)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: Boosted Density Estimation Remastered »
Tue. Jun 11th 09:20 -- 09:25 PM Room Room 102
More from the Same Authors
-
2020 Poster: Supervised learning: no loss no cry »
Richard Nock · Aditya Menon -
2019 Poster: Monge blunts Bayes: Hardness Results for Adversarial Training »
Zac Cranko · Aditya Menon · Richard Nock · Cheng Soon Ong · Zhan Shi · Christian Walder -
2019 Poster: Lossless or Quantized Boosting with Integer Arithmetic »
Richard Nock · Robert C Williamson -
2019 Oral: Lossless or Quantized Boosting with Integer Arithmetic »
Richard Nock · Robert C Williamson -
2019 Oral: Monge blunts Bayes: Hardness Results for Adversarial Training »
Zac Cranko · Aditya Menon · Richard Nock · Cheng Soon Ong · Zhan Shi · Christian Walder -
2018 Poster: Variational Network Inference: Strong and Stable with Concrete Support »
Amir Dezfouli · Edwin Bonilla · Richard Nock -
2018 Oral: Variational Network Inference: Strong and Stable with Concrete Support »
Amir Dezfouli · Edwin Bonilla · Richard Nock -
2017 Workshop: Human in the Loop Machine Learning »
Richard Nock · Cheng Soon Ong