Machine learning and high dimensional vector search

Most high-dimensional vector search methods are based on st atistical tools, signal processing approaches or graph traversal algorithms. Statistical tools include random projections [15], dimensionality reduction (PCA and the SVD). Signal processing is employed p rimarily to compress vectors with quantization [30, 4, 22] Most recent indexing methods are rely on graphs [34, 49, 3, 11] that are built with graph traversal heuristics. Vector search (VS) is used in machine learning (ML) for train ing data deduplication [39] and searching ML embeddings [28, 5]. Therefore, there are many r esearch teams around the world that are competent in both fields.