<ul><li>Principal Component Analysis (PCA) is widely used for dimensionality reduction but lacks interpretability due to dense linear combinations of features.</li><li>A novel sparse PCA algorithm is proposed that imposes sparsity through a smooth L1 penalty and utilizes a Hamiltonian formulation.</li><li>Two distinct numerical methods, Proximal Gradient (ISTA) and leapfrog (fourth-order Runge-Kutta), are employed to minimize the energy function.</li><li>Experimental evaluations on a face recognition dataset show that the proposed sparse PCA methods achieve higher classification accuracy than conventional PCA.</li></ul>

Solve sparse PCA problem by employing Hamiltonian system and leapfrog method

Discover more