English

Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold

Optimization and Control 2023-03-17 v1 Machine Learning

Abstract

We consider the problem of minimizing a non-convex function over a smooth manifold M\mathcal{M}. We propose a novel algorithm, the Orthogonal Directions Constrained Gradient Method (ODCGM) which only requires computing a projection onto a vector space. ODCGM is infeasible but the iterates are constantly pulled towards the manifold, ensuring the convergence of ODCGM towards M\mathcal{M}. ODCGM is much simpler to implement than the classical methods which require the computation of a retraction. Moreover, we show that ODCGM exhibits the near-optimal oracle complexities O(1/ε2)\mathcal{O}(1/\varepsilon^2) and O(1/ε4)\mathcal{O}(1/\varepsilon^4) in the deterministic and stochastic cases, respectively. Furthermore, we establish that, under an appropriate choice of the projection metric, our method recovers the landing algorithm of Ablin and Peyr\'e (2022), a recently introduced algorithm for optimization over the Stiefel manifold. As a result, we significantly extend the analysis of Ablin and Peyr\'e (2022), establishing near-optimal rates both in deterministic and stochastic frameworks. Finally, we perform numerical experiments which shows the efficiency of ODCGM in a high-dimensional setting.

Keywords

Cite

@article{arxiv.2303.09261,
  title  = {Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold},
  author = {Sholom Schechtman and Daniil Tiapkin and Michael Muehlebach and Eric Moulines},
  journal= {arXiv preprint arXiv:2303.09261},
  year   = {2023}
}
R2 v1 2026-06-28T09:20:04.521Z