Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms

Francesco Tonin, Alex Lambert, Panagiotis Patrinos, Johan A. K. Suykens
6/9/2023
cs.LGstat.ML

No official code found. Best implementation: taralloc/dc-kpca (6 stars, last commit 2023-06-08).

Abstract

The goal of this paper is to revisit Kernel Principal Component Analysis (KPCA) through dualization of a difference of convex functions. This allows to naturally extend KPCA to multiple objective functions and leads to efficient gradient-based algorithms avoiding the expensive SVD of the Gram matrix. Particularly, we consider objective functions that can be written as Moreau envelopes, demonstrating how to promote robustness and sparsity within the same framework. The proposed method is evaluated on synthetic and real-world benchmarks, showing significant speedup in KPCA training time as well as highlighting the benefits in terms of robustness and sparsity.

View on arXivView PDF

Code Implementations(1)

taralloc/dc-kpcaCommunity100%

Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms

60PythonMay 31, 20233 years ago

Similar Papers

Rethinking PCA Through Duality

87% match1 repo2025

A Decomposition Framework for Certifiably Optimal Orthogonal Sparse PCA

82% match2026

Duality in Multi-View Restricted Kernel Machines

80% match2023

Hidden Convexity of Fair PCA and Fast Solver via Eigenvalue Optimization

80% match1 repo2025

A Dual Formulation for Probabilistic Principal Component Analysis

78% match2023

Do algorithms and barriers for sparse principal component analysis extend to other structured settings?

78% match2023

Cite this paper

@article{tonin2023extending,
  title  = {Extending Kernel PCA through Dualization: Sparsity, Robustness and Fast Algorithms},
  author = {Francesco Tonin and Alex Lambert and Panagiotis Patrinos and Johan A. K. Suykens},
  year   = {2023},
  eprint = {2306.05815},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.05815v1},
  journal = {ICML 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.05815.svg)](https://codeofpaper.com/paper/2306.05815)

Discussion