IRFeb 12, 2015
On Projection Based Operators in Lp space for Exact Similarity Search
arXiv:1502.04032v15 citations
AI Analysis
This work addresses indexing for similarity search in high-dimensional data, but appears incremental as it builds on existing projection and Lipschitz concepts.
The paper tackled exact similarity search in high-dimensional Lp spaces by investigating indexing based on 1-Lipschitz properties and projection operators, resulting in the description of an orthogonal projection and introduction of an adaptive projection using the first principal component.
We investigate exact indexing for high dimensional Lp norms based on the 1-Lipschitz property and projection operators. The orthogonal projection that satisfies the 1-Lipschitz property for the Lp norm is described. The adaptive projection defined by the first principal component is introduced.