\chapter{Bayesian Regression Algorithms}%
\label{cha:Bayesian Regression Algorithms}

\section{Bayesian Linear Regression}%
\label{sec:Bayesian Linear Regression}
Für die Bayesian Linear Regression ist es möglich den Posterior und die Vorhersage ohne die Nutzung von Approximationen zu berechnen.
Hierzu werden die folgenden Komponenten benötigt:
\begin{itemize}
    \item Likelihood (einzelnes Sample): \tabto{6cm}$p(y|\bm x,\bm w) = \nomeq{gaussian_distribution}(y|\bm w^T \nomeq{vector_valued_function},\nomeq{variance})$
    \item Likelihood (ganzer Datensatz): \tabto{6cm}$p(\bm y|\bm X,\bm w) = \prod_i \nomeq{gaussian_distribution}(y_i|\bm w^T \bm\phi(\bm x_i), \nomeq{variance})$
    \item Gaussian Prior: \tabto{6cm}$p(\bm w) = \nomeq{gaussian_distribution}(\bm w|0,\nomeq{regularization_factor}^{-1}\nomeq{identity_matrix})$
\end{itemize}
Anschließend erfolgt die Regression nach den Schritten des \nameref{cha:Bayesian Learning}:
\begin{enumerate}
    \item Posterior errechnen:
        \begin{equation} \label{eq:bayesian_linear_regression_posterior}
            p(\bm w|\bm X,\bm y) = \frac{p(\bm y|\bm X,\bm w)p(\bm w)}{p(\bm y|\bm X)} 
                = \frac{p(\bm y|\bm X,\bm w)p(\bm w)}{\int p(\bm y|\bm X,\bm w)p(\bm w)d\bm w}
        \end{equation}
        Hierfür kann die 2. Gaussian Bayes Rule (\cref{sec:Gaussian Bayes Rules}) verwendet werden\\
        (mit $\bm\mu_{\bm x}=0$, $\nomeq{covariance}_{\bm x} = \nomeq{regularization_factor}^{-1}$, $\bm F = \bm\Phi$ und $\sigma_{\bm y}^2 = \sigma_{\bm y}^2$)
        \begin{equation} \label{eq:bayesian_linear_regression_posterior_gaussian_bayes_rule}
            p(\bm w|\bm X,\bm y) = \nomeq{gaussian_distribution}(\bm w|\bm\mu_{\bm w|\bm X,\bm y},\nomeq{covariance}_{\bm w|\bm X,\bm y}) 
        \end{equation}
        \begin{itemize}
            \item $\bm\mu_{\bm w|\bm X,\bm y} = (\bm\Phi^T\bm\Phi + \sigma_{\bm y}^2\nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}\bm\Phi^T\bm y$
            \item $\nomeq{covariance}_{\bm w|\bm X,\bm y} = \sigma_{\bm y}^2(\bm\Phi^T\bm\Phi + \sigma_{\bm y}^2\nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}$
        \end{itemize}
    \item Predictive Distribution errechnen:
        \begin{align} \label{eq:bayesion_linear_regression_predictive_distribution}
            p(y^*|\bm x^*,\bm X,\bm y) &= \int p(y^*|\bm w,\bm x^*)p(\bm w|\bm X,\bm y)d\bm w \\
            &= \int \nomeq{gaussian_distribution}(y_*|\phi_*^T\bm w,\sigma_{\bm y}^2)\nomeq{gaussian_distribution}(\bm w|\bm\mu_{\bm w|\bm X,\bm y},\nomeq{covariance}_{\bm w|\bm X,\bm y}) d\bm w
        \end{align}
        Um diese Gleichung zu lösen kann die \nameref{sec:Gaussian Propagation} (\cref{sec:Gaussian Propagation}) verwendet werden:
        \begin{itemize}
            \item $\nomeq{mean}(\bm x^*) = \phi(\bm x^*)^T(\bm\Phi^T\bm\Phi + \nomeq{regularization_factor}\sigma_{\bm y}^2\nomeq{identity_matrix})^{-1}\bm\Phi^T\bm y$
            \item $\nomeq{variance}(\bm x^*) = \sigma_{\bm y}^2(1+\phi(\bm x^*)^T(\bm\Phi^T\bm\Phi + \nomeq{regularization_factor}\sigma_{\bm y}^2\nomeq{identity_matrix})^{-1}\phi(\bm x^*))$
        \end{itemize}
\end{enumerate}
Es fällt auf, dass $\nomeq{mean}(\bm{x^*})$ sich im Vergleich zur \nameref{sub:Ridge Regression} nicht verändert hat.
Allerdings ist $\nomeq{variance}(\bm x^*)$ jetzt abhängig von den Eingangsdaten.