Eigenvector Component Calculation Speedup over NumPy for High-Performance Computing
Abstract
Applications related to artificial intelligence, machine learning, and system identification simulations essentially use eigenvectors. Calculating eigenvectors for very large matrices using conventional methods is compute-intensive and renders the applications slow. Recently, Eigenvector-Eigenvalue Identity formula promising significant speedup was identified. We study the algorithmic implementation of the formula against the existing state-of-the-art algorithms and their implementations to evaluate the performance gains. We provide a first of its kind systematic study of the implementation of the formula. We demonstrate further improvements using high-performance computing concepts over native NumPy eigenvector implementation which uses LAPACK and BLAS.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2020
- DOI:
- 10.48550/arXiv.2002.04989
- arXiv:
- arXiv:2002.04989
- Bibcode:
- 2020arXiv200204989D
- Keywords:
-
- Computer Science - Performance;
- Computer Science - Distributed;
- Parallel;
- and Cluster Computing;
- Computer Science - Data Structures and Algorithms
- E-Print:
- Accepted at 8th International Conference on Recent Trends in Computing (ICRTC 2020), to be published in Springer Lecture Notes in Networks and Systems (LNNS)