Using the Distance Distribution for Approximate Similarity Queries in High-Dimensional Metric Spaces

We investigate the problem of approximate similarity (nearest neighbor) search in high-dimensional metric spaces, and describe how the distance distribution of the query object can be exploited so as to provide probabilistic guarantees on the quality of the result. This leads to a new paradigm for similarity search, called PAC-NN (probably approximately correct nearest neighbor) queries, aiming to break the "dimensionality curse". PAC-NN queries return, with probability at least 1 ; , a (1 + )-approximate NN

• Type: Conference
• Year: 1999
• Where: DEXAW
• Authors: Paolo Ciaccia, Marco Patella
• Keywords: Approximate Similarity, Correct Nearest Neighbor, Database, DEXAW 1999, PAC-NN Queries