Fast and Accurate Pseudoinverse with Sparse Matrix Reordering and Incremental Approach
This addresses a bottleneck in solving linear systems for large, sparse datasets, offering a practical improvement for multi-label regression and similar tasks.
The paper tackles the problem of efficiently and accurately computing the pseudoinverse of sparse feature matrices for optimization in machine learning, proposing FastPI, which uses incremental SVD and matrix reordering to achieve faster computation than other approximate methods without loss of accuracy.
How can we compute the pseudoinverse of a sparse feature matrix efficiently and accurately for solving optimization problems? A pseudoinverse is a generalization of a matrix inverse, which has been extensively utilized as a fundamental building block for solving linear systems in machine learning. However, an approximate computation, let alone an exact computation, of pseudoinverse is very time-consuming due to its demanding time complexity, which limits it from being applied to large data. In this paper, we propose FastPI (Fast PseudoInverse), a novel incremental singular value decomposition (SVD) based pseudoinverse method for sparse matrices. Based on the observation that many real-world feature matrices are sparse and highly skewed, FastPI reorders and divides the feature matrix and incrementally computes low-rank SVD from the divided components. To show the efficacy of proposed FastPI, we apply them in real-world multi-label linear regression problems. Through extensive experiments, we demonstrate that FastPI computes the pseudoinverse faster than other approximate methods without loss of accuracy. %and uses much less memory compared to full-rank SVD based approach. Results imply that our method efficiently computes the low-rank pseudoinverse of a large and sparse matrix that other existing methods cannot handle with limited time and space.