%0 Conference Paper %1 Skala2005DistanceIndexingDifficulty %A Skala, Matthew %B String Processing and Information Retrieval %C Berlin, Heidelberg %D 2005 %E Consens, Mariano %E Navarro, Gonzalo %I Springer Berlin Heidelberg %K distance-based-indexing distance-metrics high-dimensional-data high-dimensional-indexing %P 103--114 %T Measuring the Difficulty of Distance-Based Indexing %X Data structures for similarity search are commonly evaluated on data in vector spaces, but distance-based data structures are also applicable to non-vector spaces with no natural concept of dimensionality. The intrinsic dimensionality statistic of Chávez and Navarro provides a way to compare the performance of similarity indexing and search algorithms across different spaces, and predict the performance of index data structures on non-vector spaces by relating them to equivalent vector spaces. We characterise its asymptotic behaviour, and give experimental results to calibrate these comparisons. %@ 978-3-540-32241-2

@inproceedings{Skala2005DistanceIndexingDifficulty, abstract = {Data structures for similarity search are commonly evaluated on data in vector spaces, but distance-based data structures are also applicable to non-vector spaces with no natural concept of dimensionality. The intrinsic dimensionality statistic of Ch{\'a}vez and Navarro provides a way to compare the performance of similarity indexing and search algorithms across different spaces, and predict the performance of index data structures on non-vector spaces by relating them to equivalent vector spaces. We characterise its asymptotic behaviour, and give experimental results to calibrate these comparisons.}, added-at = {2019-06-26T23:45:55.000+0200}, address = {Berlin, Heidelberg}, author = {Skala, Matthew}, biburl = {https://www.bibsonomy.org/bibtex/29cce62a0867de7eea83ba5a8d3434e07/salotz}, booktitle = {String Processing and Information Retrieval}, description = {Measuring the Difficulty of Distance-Based Indexing | SpringerLink}, editor = {Consens, Mariano and Navarro, Gonzalo}, interhash = {216f8bb0d990dd18a11bbc0d17cbafd3}, intrahash = {9cce62a0867de7eea83ba5a8d3434e07}, isbn = {978-3-540-32241-2}, keywords = {distance-based-indexing distance-metrics high-dimensional-data high-dimensional-indexing}, pages = {103--114}, publisher = {Springer Berlin Heidelberg}, timestamp = {2019-06-26T23:45:55.000+0200}, title = {Measuring the Difficulty of Distance-Based Indexing}, year = 2005 }