Hopefully final draft

content/experiments/experiments.tex

@@ -73,7 +73,7 @@ We compare \textsc{ROLL}-AOC (the primary proposed loss, optimising the area und
   \item \textbf{MAE}: mean absolute error (symmetric noise-robust loss).
 \end{itemize}
 
-All methods use the same network architecture, optimiser (Adam for non-LibAUC methods), and early stopping. The best model per-episode is chosen from the epoch with lowest loss. Each configuration is run for $n = 5$ independent episodes on KEEL and the tabular large datasets, $n = 3$ on CIFAR-10N and Food-101N. Reported AUC is evaluated on the test split, averaged between episodes.
+All methods use the same network architecture, optimiser (Adam for non-LibAUC methods), and early stopping. The best model per-episode is chosen from the epoch with lowest loss. Each configuration is run for $n = 5$ independent episodes across all datasets. The KEEL noise experiments (\Cref{sec:results:keel}) use $n = 10$ instead: KEEL's datasets are small enough that each episode trains quickly despite the number of datasets involved, making it practical to run more episodes there for a more reliable noise-robustness comparison. Reported AUC is evaluated on the test split, averaged between episodes.
 
 \section{Results}\label{sec:experiments:results}
 \addcontentsline{tocheb}{section}{\protect\numberline{\secnumforhebrewtoc}{תוצאות}}
@@ -154,7 +154,7 @@ Yeast3       & \textbf{0.879{\tiny{$\pm$0.032}}} & 0.861{\tiny{$\pm$0.070}} & 0.
 
 \begin{table}[htbp]
 \centering
-\caption{Mean test AUC ($\pm$\,std, $n=3$ episodes) on CIFAR-10N under three label-noise levels. Best per row in \textbf{bold}.}
+\caption{Mean test AUC ($\pm$\,std, $n=5$ episodes) on CIFAR-10N under three label-noise levels. Best per row in \textbf{bold}.}
 \label{tab:results:cifar10n}
 \resizebox{\textwidth}{!}{%
 \begin{tabular}{lccccccc}
@@ -182,7 +182,7 @@ On Food-101N, \textsc{ROLL}-AOC again achieves the highest AUC ($0.867\pm0.004$)
 
 \begin{table}[htbp]
 \centering
-\caption{Mean test AUC ($\pm$\,std) on large real-world datasets ($n=5$ episodes; Food-101N and ChestXray14: $n=3$). Best per row in \textbf{bold}. ChestXray14 uses frozen DenseNet-121 embeddings; Food-101N trains end-to-end on raw pixels. LibAUC on Food-101N uses no sigmoid on model outputs.}
+\caption{Mean test AUC ($\pm$\,std, $n=5$ episodes) on large real-world datasets. Best per row in \textbf{bold}. ChestXray14 uses frozen DenseNet-121 embeddings; Food-101N trains end-to-end on raw pixels. LibAUC on Food-101N uses no sigmoid on model outputs.}
 \label{tab:results:large}
 \resizebox{\textwidth}{!}{%
 \begin{tabular}{lccccccc}
@@ -193,8 +193,8 @@ Bank Marketing        & 0.931{\tiny{$\pm$0.002}} & 0.580{\tiny{$\pm$0.040}} & 0.
 Credit Card Fraud     & \textbf{0.968{\tiny{$\pm$0.001}}} & 0.949{\tiny{$\pm$0.015}} & 0.942{\tiny{$\pm$0.020}} & 0.940{\tiny{$\pm$0.013}} & 0.948{\tiny{$\pm$0.014}} & 0.966{\tiny{$\pm$0.006}} & 0.954{\tiny{$\pm$0.009}} \\
 Home Credit           & \textbf{0.712{\tiny{$\pm$0.001}}} & 0.693{\tiny{$\pm$0.002}} & 0.694{\tiny{$\pm$0.002}} & 0.688{\tiny{$\pm$0.003}} & 0.698{\tiny{$\pm$0.002}} & 0.711{\tiny{$\pm$0.001}} & 0.699{\tiny{$\pm$0.004}} \\
 \midrule
-ChestXray14 (Effusion) & \textbf{0.839{\tiny{$\pm$0.001}}} & 0.788{\tiny{$\pm$0.008}} & 0.798{\tiny{$\pm$0.009}} & 0.729{\tiny{$\pm$0.007}} & 0.829{\tiny{$\pm$0.004}} & 0.835{\tiny{$\pm$0.002}} & 0.810{\tiny{$\pm$0.001}} \\
-Food-101N             & \textbf{0.867{\tiny{$\pm$0.004}}} & 0.848{\tiny{$\pm$0.025}} & 0.847{\tiny{$\pm$0.009}} & 0.845{\tiny{$\pm$0.032}} & 0.842{\tiny{$\pm$0.006}} & 0.857{\tiny{$\pm$0.002}} & 0.855{\tiny{$\pm$0.013}} \\
+ChestXray14 (Effusion) & \textbf{0.838{\tiny{$\pm$0.001}}} & 0.790{\tiny{$\pm$0.010}} & 0.799{\tiny{$\pm$0.011}} & 0.731{\tiny{$\pm$0.008}} & 0.828{\tiny{$\pm$0.003}} & 0.836{\tiny{$\pm$0.002}} & 0.811{\tiny{$\pm$0.002}} \\
+Food-101N             & \textbf{0.867{\tiny{$\pm$0.005}}} & 0.851{\tiny{$\pm$0.026}} & 0.848{\tiny{$\pm$0.010}} & 0.842{\tiny{$\pm$0.033}} & 0.844{\tiny{$\pm$0.006}} & 0.858{\tiny{$\pm$0.003}} & 0.854{\tiny{$\pm$0.012}} \\
 \bottomrule
 \end{tabular}%
 }