\BOOKMARK [0][-]{Doc-Start}{Lecture 20 \205 CTR Predictions and Literature References}{}% 1
\BOOKMARK [1][-]{section.1}{Ad Click Prediction: a view from the trenches}{Doc-Start}% 2
\BOOKMARK [2][-]{subsection.1.1}{FTRL-Proximal Online Learning Algorithms}{section.1}% 3
\BOOKMARK [2][-]{subsection.1.2}{Per-Coordinate Learning Rates}{section.1}% 4
\BOOKMARK [2][-]{subsection.1.3}{Techniques for saving memory}{section.1}% 5
\BOOKMARK [3][-]{subsubsection.1.3.1}{Probabilistic Feature Inclusion}{subsection.1.3}% 6
\BOOKMARK [3][-]{subsubsection.1.3.2}{Storing coefficients with fewer bits: Randomized Rounding}{subsection.1.3}% 7
\BOOKMARK [3][-]{subsubsection.1.3.3}{Training many similar models Grouped}{subsection.1.3}% 8
\BOOKMARK [2][-]{subsection.1.4}{High-Dimensional Data Visualization for Model Accuracy}{section.1}% 9
\BOOKMARK [2][-]{subsection.1.5}{Automated Feature Management System}{section.1}% 10
\BOOKMARK [2][-]{subsection.1.6}{Final remarks about the paper}{section.1}% 11
\BOOKMARK [1][-]{section.2}{References and Other Topics}{Doc-Start}% 12