Sparse Orthogonality-Constrained Optimization via ADPMM

Optimization problems with orthogonality constraints arise throughout machine learning, including dimensionality reduction, clustering, and representation learning. These problems require the... Continue

Simplex-Constrained Incoherent Matrix Factorization with Hybrid Mirror Descent

Matrix factorization is a fundamental tool in data mining and machine learning, with applications in clustering, topic modeling, recommender systems,... Continue

FISTA

“Fast iterative shrinkage-thresholding algorithm”(FISTA) is a proximal gradient method that aims to solve convex optimization problems of the form: \[\min_x... Continue