Bolt: Accelerated Data Mining with Fast Vector Compression
Name
1706.10283.pdf
Description
Submitted version
Size
1.91 MB
Format
Adobe PDF
Checksum (MD5)
0c381d621fb4b7b2926d747d2248f12b
Author(s)
Blalock, Davis W.
Guttag, John V.
Date Issued
August 2017
Publisher
Association for Computing Machinery (ACM)
Citation
Blalock, Davis W. and Guttag, John V. 2017. "Bolt: Accelerated Data Mining with Fast Vector Compression."
Version
Original manuscript
Abstract
© 2017 Copyright held by the owner/author(s). Vectors of data are at the heart of machine learning and data mining. Recently, vector quantization methods have shown great promise in reducing both the time and space costs of operating on vectors. We introduce a vector quantization algorithm that can compress vectors over 12x faster than existing techniques while also accelerating approximate vector operations such as distance and dot product computations by up to 10x. Because it can encode over 2GB of vectors per second, it makes vector quantization cheap enough to employ in many more circumstances. For example, using our technique to compute approximate dot products in a nested loop can multiply matrices faster than a state-of-the-art BLAS implementation, even when our algorithm must first compress the matrices. In addition to showing the above speedups, we demonstrate that our approach can accelerate nearest neighbor search and maximum inner product search by over 100x compared to floating point operations and up to 10x compared to other vector quantization methods. Our approximate Euclidean distance and dot product computations are not only faster than those of related algorithms with slower encodings, but also faster than Hamming distance computations, which have direct hardware support on the tested platforms. We also assess the errors of our algorithm's approximate distances and dot products, and find that it is competitive with existing, slower vector quantization algorithms.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3097983.3098195
