commit 003a4329417474dbe3374ebc444fa6d1d94d99bb
parent c7b4e8ac2c6a6d10d11c26b2258e9ff22c06a38c
Author: Silas Brack <s174433@student.dtu.dk>
Date: Sun, 12 Feb 2023 13:35:53 +0100
Meh.
Diffstat:
5 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/chapters/ablation_experiments.tex b/chapters/ablation_experiments.tex
@@ -1,6 +1,6 @@
\setchapterpreamble[u]{\margintoc}
\chapter{Ablation Experiments}
-\label{ch:ablation-experiments}
+\labch{ablation-experiments}
\section{Hessian-Vector Products}[Hessian-Vector Products]
diff --git a/chapters/experiments.tex b/chapters/experiments.tex
@@ -1,6 +1,6 @@
\setchapterpreamble[u]{\margintoc}
\chapter{Experiments}
-\label{ch:experiments}
+\labch{experiments}
In \cref{ch:ablation-experiments} we tested whether the approximate sampling scheme is able to produce correct posterior samples on an arbitrary network.
In this chapter, we use our custom bound on the marginal likelihood to train a Bayesian neural network on the marginal via online Laplace.
diff --git a/chapters/laplace.tex b/chapters/laplace.tex
@@ -1,6 +1,6 @@
\setchapterpreamble[u]{\margintoc}
\chapter{The Laplace Approximation}
-\label{ch:laplace}
+\labch{laplace}
% http://saul.cpsc.ucalgary.ca/pmwiki.php/GradTips/GradTipsLiteratureReview
In this chapter, we discuss training and inference in deep learning from a Bayesian perspective.
diff --git a/chapters/sampling.tex b/chapters/sampling.tex
@@ -1,6 +1,6 @@
\setchapterpreamble[u]{\margintoc}
\chapter{Sampling}
-\label{ch:sampling}
+\labch{sampling}
We will now discuss how to perform inference by sampling from the Laplace posterior distribution.
We first give an overview of how we typically sample from the Laplace posterior and discuss the memory constraints of this sampling method when using the full posterior precision matrix.
diff --git a/chapters/training.tex b/chapters/training.tex
@@ -1,6 +1,6 @@
\setchapterpreamble[u]{\margintoc}
\chapter{Training}
-\label{ch:training}
+\labch{training}
In this chapter, we will discuss training neural networks by maximising the evidence under the Laplace approximation.
We first motivate maximising the evidence as opposed to maximising the posterior and discuss how the Laplace approximation guarantees the feasibility of the evidence, as well as the issues that arise when computing the marginal likelihood with the full posterior precision.
