Example: The Johnson-Lindenstrauss bound for embedding with random projections
The Johnson-Lindenstrauss bound for embedding with random projections
The Johnson-Lindenstrauss lemma states that any high dimensional dataset can be randomly projected into a lower dimensional Euclidean space while controlling the distortion in the pairwise distances.
Theoretical bounds
The distortion introduced by a random projection p is asserted by the fact that p is defining an eps-embedding with good probability as defined by:
