Back to Search Start Over

Optimization without Retraction on the Random Generalized Stiefel Manifold

Authors :
Vary, Simon
Ablin, Pierre
Gao, Bin
Absil, P. -A.
Vary, Simon
Ablin, Pierre
Gao, Bin
Absil, P. -A.
Publication Year :
2024

Abstract

Optimization over the set of matrices $X$ that satisfy $X^\top B X = I_p$, referred to as the generalized Stiefel manifold, appears in many applications involving sampled covariance matrices such as the canonical correlation analysis (CCA), independent component analysis (ICA), and the generalized eigenvalue problem (GEVP). Solving these problems is typically done by iterative methods that require a fully formed $B$. We propose a cheap stochastic iterative method that solves the optimization problem while having access only to a random estimates of $B$. Our method does not enforce the constraint in every iteration; instead, it produces iterations that converge to critical points on the generalized Stiefel manifold defined in expectation. The method has lower per-iteration cost, requires only matrix multiplications, and has the same convergence rates as its Riemannian optimization counterparts that require the full matrix $B$. Experiments demonstrate its effectiveness in various machine learning applications involving generalized orthogonality constraints, including CCA, ICA, and the GEVP.<br />Comment: This v2 is the camera-ready version for ICML 2024

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1438552786
Document Type :
Electronic Resource