Reliable, efficient and light distance computation on high-dimensional vectors

• Main Author: Gao, Jianyang
• Other Authors: Long Cheng
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2025
• Subjects: Computer and Information Science; Approximate nearest neighbor search; Johnson-Lindenstrauss transformation; Quantization
• Online Access: https://hdl.handle.net/10356/182813
• Institution: Nanyang Technological University

The great advances in deep learning enable human beings to extract the semantic information in ubiquitous unstructured data into high-dimensional vectors, leading to an urgent priority of managing vector data. Nearest neighbor (NN) query is a pivotal question in vector data management. Unfortunately...