Browse Source

Remove obsolete todo

icml
Markus Kaiser 3 years ago
parent
commit
785075ebb9
  1. 1
      dynamic_dirichlet_deep_gp.tex

1
dynamic_dirichlet_deep_gp.tex

@ -466,7 +466,6 @@ We use an implementation of DAGP in TensorFlow~\parencite{tensorflow2015-whitepa
\subsection{Noise Separation}
\label{subsec:choicenet}
\todo[inline]{Should we emphasize that the noise prior is wrong (Gaussian vs. uniform) and it still works?}
We begin with an experiment based on a noise separation problem.
We apply DAGP to a one-dimensional regression problem with uniformly distributed outliers in the training data.
We use a task proposed by~\textcite{choi_choicenet_2018} where we sample inputs $x \in [-3, 3]$ uniformly and apply the function $\Fun{f}{x} = (1 - \delta)\Fun{\cos}{\sfrac{\pi}{2} \cdot x}\Fun{\exp}{-(\sfrac{x}{2})^2} + \delta \cdot \epsilon$, where $\delta \sim \Fun{\Ber}{\lambda}$ and $\epsilon \sim \Fun{\Uni}{-1, 3}$.

Loading…
Cancel
Save