Files
eth-summaries/semester4/dmdb/parts/06_vector-search/02_hash-index.tex
T
janishutz c82ceca4e0 [DMDB] Add concurrency control and recovery
Oops, luckily still figured out that that was missing...
2026-07-25 18:58:39 +02:00

17 lines
965 B
TeX

\subsection{Hash Index}
To measure the quality of \acrshort{ann} in comparison to \acrshort{knn}, we use $\texttt{recall@k} = |\texttt{ANN\_result} \cap \texttt{KNN\_result}| \div k$.
This however is not always a good metric, as two vastly different results, one objectively worse can score equally well.
Alternative methods mentioned are \texttt{RDE@k} and \texttt{TDK@k}, but not elaborated any further.
\subsubsection{Performance vs Recall Trade-off}
This is a challenging task, primarily focusing on how many vectors we need to visit to achieve a user-specified target recall.
A few explored strategies are:
\begin{itemize}
\item \bi{Uniform autotuning for all queries}: Using learned offline models (e.g. Google CloudSQL VectorAssist)
\item \bi{Different for each query}: A model predicts the search effort parameters for each query or index
\item \bi{Adaptive}: Decide to continue or stop early based on the current search state
\end{itemize}