Unlocking the Potential of Non-PSD Kernel Matrices: A Polar Decomposition-based Transformation for Improved Prediction Models
Open Access
- 21 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1867-1876
Abstract
Kernel functions are a key element in many machine learning methods to capture the similarity between data points. However, a considerable number of these functions do not meet all mathematical requirements to be a valid positive semi-definite kernel, a crucial precondition for kernel-based classifiers such as Support Vector Machines or Kernel Fisher Discriminant classifiers. In this paper, we propose a novel strategy employing a polar decomposition to effectively transform invalid kernel matrices to positive semi-definite matrices, while preserving the topological structure inherent to the data points. Utilizing polar decomposition allows the effective transformation of indefinite kernel matrices from Krein space to positive semi-definite matrices in Hilbert space, thereby providing an efficient out-of-sample extension for new unseen data and enhancing kernel method applicability across diverse classification tasks. We evaluate our approach on a variety of benchmark datasets and demonstrate its superiority over competitive methods.Keywords
This publication has 31 references indexed in Scilit:
- Metric and non-metric proximity transformations at linear costsNeurocomputing, 2015
- Indefinite Proximity Learning: A ReviewNeural Computation, 2015
- Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix DecompositionsSIAM Review, 2011
- Edit distance-based kernel functions for structural pattern classificationPattern Recognition, 2006
- Appendix E: Introduction to PRTools2004
- A survey of kernels for structured dataACM SIGKDD Explorations Newsletter, 2003
- The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003Nucleic Acids Research, 2003
- Pairwise data clustering by deterministic annealingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Computing the Polar Decomposition—with ApplicationsSIAM Journal on Scientific and Statistical Computing, 1986
- Linear operators in spaces with indefinite metric and their applicationsJournal of Mathematical Sciences, 1981