Block Coordinate Descent Methods for Optimization under J-Orthogonality Constraints with Applications

TL;DR

This paper introduces JOBCD, a novel block coordinate descent method for optimization problems with J-orthogonality constraints, demonstrating superior performance on various hyperbolic problems and establishing theoretical convergence guarantees.

Contribution

The paper proposes JOBCD and its variants, providing the first convergence analysis and oracle complexity results for optimization under J-orthogonality constraints.

Findings

JOBCD outperforms existing methods on hyperbolic eigenvalue problems.

VR-J-JOBCD reduces oracle complexity through variance reduction.

Extensive experiments validate the effectiveness of the proposed algorithms.

Abstract

The J-orthogonal matrix, also referred to as the hyperbolic orthogonal matrix, is a class of special orthogonal matrix in hyperbolic space, notable for its advantageous properties. These matrices are integral to optimization under J-orthogonal constraints, which have widespread applications in statistical learning and data science. However, addressing these problems is generally challenging due to their non-convex nature and the computational intensity of the constraints. Currently, algorithms for tackling these challenges are limited. This paper introduces JOBCD, a novel Block Coordinate Descent method designed to address optimizations with J-orthogonality constraints. We explore two specific variants of JOBCD: one based on a Gauss-Seidel strategy (GS-JOBCD), the other on a variance-reduced and Jacobi strategy (VR-J-JOBCD). Notably, leveraging the parallel framework of a Jacobi strategy, VR-J-JOBCD integrates variance reduction techniques to decrease oracle complexity in the minimization of finite-sum functions. For both GS-JOBCD and VR-J-JOBCD, we establish the oracle complexity under mild conditions and strong limit-point convergence results under the Kurdyka-Lojasiewicz inequality. To demonstrate the effectiveness of our method, we conduct experiments on hyperbolic eigenvalue problems, hyperbolic structural probe problems, and the ultrahyperbolic knowledge graph embedding problem. Extensive experiments using both real-world and synthetic data demonstrate that JOBCD consistently outperforms state-of-the-art solutions, by large margins.