Upodate presentation (CRPS Simulations)

index.qmd

@@ -956,20 +956,27 @@ for( t in 1:T ) {
 
 ## Simulation Study
 
+::: {.panel-tabset}
+
+## BOA
+
 :::: {.columns}
 
 ::: {.column width="48%"}
 
-Data Generating Process of the [simple probabilistic example](#simple_example)
+Data Generating Process of the [simple probabilistic example](#simple_example):
+
+\begin{align*}
+  Y_t &\sim \mathcal{N}(0,\,1)\\
+  \widehat{X}_{t,1} &\sim \widehat{F}_{1}=\mathcal{N}(-1,\,1) \\
+  \widehat{X}_{t,2} &\sim \widehat{F}_{2}=\mathcal{N}(3,\,4)
+\end{align*}
 
 - Constant solution $\lambda \rightarrow \infty$
 - Pointwise Solution of the proposed BOAG
 - Smoothed Solution of the proposed BOAG
   - Weights are smoothed during learning
   - Smooth weights are used to calculate Regret, adjust weights, etc. 
-- Smooth ex-post solution
-  - Weights are smoothed after the learning
-  - Algorithm always uses non-smoothed weights
 
 :::
 
@@ -983,6 +990,8 @@ Data Generating Process of the [simple probabilistic example](#simple_example)
 
 ## QL Deviation
 
+Deviation from best attainable QL (1000 runs). 
+
 ![](assets/crps_learning/pre_vs_post.gif)
 
 ## CRPS vs. Lambda
@@ -991,13 +1000,19 @@ CRPS Values for different $\lambda$ (1000 runs)
 
 ![](assets/crps_learning/pre_vs_post_lambda.gif)
 
+## Knots
+
+CRPS for different number of knots (1000 runs)
+
+![](assets/crps_learning/pre_vs_post_kstep.gif)
+
 ::::
 
 :::
 
 ::::
 
-## Simulation Study
+## Comparison to EWA and ML-Poly
 
 The same simulation carried out for different algorithms (1000 runs):
 
@@ -1005,6 +1020,10 @@ The same simulation carried out for different algorithms (1000 runs):
 <img src="assets/crps_learning/algos_constant.gif">
 </center>
 
+## Study Forget
+
+::::
+
 ## Simulation Study
 
 :::: {.columns}