Searcharxiv⌕ Search

arXiv subjects

Florentin Goyens

Publications and source records attributed to Florentin Goyens.

9 recordsLinked to original sources
arXiv2026

Complexity guarantees and polling strategies for Riemannian direct-search methods

Direct-search algorithms are derivative-free optimization techniques that operate by polling the variable space along specific directions forming positive spanning sets (PSSs). When the problem variables are constrained to lie on a Riemannian manifold, polling must be performed along tangent directions. Although Riemannian variants of direct search have already been proposed and endowed with asymptotic guarantees, a proper generalization of PSSs on manifolds remains to be investigated. In particular, a measure of quality for those PSSs is required to obtain complexity bounds for direct search. In this paper, we derive complexity guarantees for a class of Riemannian direct-search techniques, and study two ways of generating positive spanning sets in tangent spaces. We pay particular attention to the unit hypersphere case, for which we establish that generating directions directly within the tangent space leads to better complexity properties than projecting PSSs from the ambient space onto the tangent space. Our numerical experiments highlight the impact of dimension and codimension in more general settings.

math.OC↗
arXiv2026

The sketched landing method for large-scale optimization under orthogonality constraints

We propose the sketched landing method, a randomized variant of the landing method for optimization under orthogonality constraints. Each landing step consists of the sum of a normal component, which reduces infeasibility, and a tangent component, which decreases the objective function. Our main contribution is the introduction of low-dimensional random sketch matrices to reduce the computational cost of these directions. We consider both dense (Gaussian) and sparse (subsampling) sketch matrices, and show how they reduce the per-iteration cost while preserving convergence guarantees in expectation.

math.OC↗
arXiv2026

The Riemannian Landing Method: From projected gradient flows to SQP

Landing methods have recently emerged in Riemannian matrix optimization as efficient schemes for handling nonlinear equality constraints without resorting to costly retractions. These methods decompose the search direction into tangent and normal components, enabling asymptotic feasibility while maintaining inexpensive updates. In this work, we provide a unifying geometric framework which reveals that, under suitable choices of Riemannian metric, the landing algorithm encompasses several classical optimization methods such as projected and null-space gradient flows, Sequential Quadratic Programming (SQP), and a certain form of the augmented Lagrangian method. In particular, we show that a quadratically convergent landing method essentially reproduces the quadratically convergent SQP method. These connections also allow us to propose a globally convergent landing method using adaptive step sizes. The backtracking line search satisfies an Armijo condition on a merit function, and does not require prior knowledge of Lipschitz constants. Our second key contribution is to analyze landing methods through a geometric parameterization of the metric in terms of fields of oblique projectors and associated metric restrictions. This viewpoint disentangles the roles of orthogonality, tangent and normal metrics, and elucidates how to design the metric to obtain explicit tangent and normal updates. For matrix optimization, this framework not only recovers recent constructions in the literature for problems with orthogonality constraints, but also provides systematic guidelines for designing new metrics that admit closed-form search directions.

math.OC↗
arXiv2026

Complexity of quadratic penalty methods with adaptive accuracy under a PL condition for the constraints

We study the quadratic penalty method (QPM) for smooth nonconvex optimization problems with equality constraints. Assuming the constraint violation satisfies the PL condition near the feasible set, we derive sharper worst-case complexity bounds for obtaining approximate first-order KKT points. When the objective and constraints are twice continuously differentiable, we show that QPM equipped with a suitable first-order inner solver requires at most $O(\varepsilon_{0}^{-1}\varepsilon_{1}^{-2})$ first-order oracle calls to find an $(\varepsilon_{0},\varepsilon_{1})$-approximate KKT point -- that is, a point that is $\varepsilon_{0}$-approximately feasible and $\varepsilon_{1}$-approximately stationary. Furthermore, when the objective and constraints are three times continuously differentiable, we show that QPM with a suitable second-order inner solver requires at most $O\left(\varepsilon_{0}^{-1/2}\varepsilon_{1}^{-3/2}\right)$ second-order oracle calls to find an $(\varepsilon_{0},\varepsilon_{1})$-approximate KKT point. We also introduce an adaptive, feasibility-aware stopping criterion for the subproblems, which relaxes the stationarity tolerance when far from feasibility. This rule preserves all theoretical guarantees while substantially reducing computational effort in practice.

math.OC↗
arXiv2024

Riemannian trust-region methods for strict saddle functions with complexity guarantees

The difficulty of minimizing a nonconvex function is in part explained by the presence of saddle points. This slows down optimization algorithms and impacts worst-case complexity guarantees. However, many nonconvex problems of interest possess a favorable structure for optimization, in the sense that saddle points can be escaped efficiently by appropriate algorithms. This strict saddle property has been extensively used in data science to derive good properties for first-order algorithms, such as convergence to second-order critical points. However, the analysis and the design of second-order algorithms in the strict saddle setting have received significantly less attention. In this paper, we consider second-order trust-region methods for a class of strict saddle functions defined on Riemannian manifolds. These functions exhibit (geodesic) strong convexity around minimizers and negative curvature at saddle points. We show that the standard trust-region method with exact subproblem minimization finds an approximate local minimizer in a number of iterations that depends logarithmically on the accuracy parameter, which significantly improves known results for general nonconvex optimization. We also propose an inexact variant of the algorithm that explicitly leverages the strict saddle property to compute the most appropriate step at every iteration. Our bounds for the inexact variant also improve over the general nonconvex case, and illustrate the benefit of using strict saddle properties within optimization algorithms. Keywords: Riemannian optimization, strict saddle function, second-order method, complexity guarantees.

math.OC↗
arXiv2024

Computing second-order points under equality constraints: revisiting Fletcher's augmented Lagrangian

We address the problem of minimizing a smooth function under smooth equality constraints. Under regularity assumptions on these constraints, we propose a notion of approximate first- and second-order critical point which relies on the geometric formalism of Riemannian optimization. Using a smooth exact penalty function known as Fletcher's augmented Lagrangian, we propose an algorithm to minimize the penalized cost function which reaches $\varepsilon$-approximate second-order critical points of the original optimization problem in at most $\mathcal{O}(\varepsilon^{-3})$ iterations. This improves on current best theoretical bounds. Along the way, we show new properties of Fletcher's augmented Lagrangian, which may be of independent interest.

math.OC↗
arXiv2024

Registration of algebraic varieties using Riemannian optimization

We consider the point cloud registration problem, the task of finding a transformation between two point clouds that represent the same object but are expressed in different coordinate systems. Our approach is not based on a point-to-point correspondence, matching every point in the source point cloud to a point in the target point cloud. Instead, we assume and leverage a low-dimensional nonlinear geometric structure of the data. Firstly, we approximate each point cloud by an algebraic variety (a set defined by finitely many polynomial equations). This is done by solving an optimization problem on the Grassmann manifold, using a connection between algebraic varieties and polynomial bases. Secondly, we solve an optimization problem on the orthogonal group to find the transformation (rotation $+$ translation) which makes the two algebraic varieties overlap. We use second-order Riemannian optimization methods for the solution of both steps. Numerical experiments on real and synthetic data are provided, with encouraging results. Our approach is particularly useful when the two point clouds describe different parts of an objects (which may not even be overlapping), on the condition that the surface of the object may be well approximated by a set of polynomial equations. The first procedure -- the approximation -- is of independent interest, as it can be used for denoising data that belongs to an algebraic variety. We provide statistical guarantees for the estimation error of the denoising using Stein's unbiased estimator.

math.OC↗
arXiv2022

Nonlinear matrix recovery using optimization on the Grassmann manifold

We investigate the problem of recovering a partially observed high-rank matrix whose columns obey a nonlinear structure such as a union of subspaces, an algebraic variety or grouped in clusters. The recovery problem is formulated as the rank minimization of a nonlinear feature map applied to the original matrix, which is then further approximated by a constrained non-convex optimization problem involving the Grassmann manifold. We propose two sets of algorithms, one arising from Riemannian optimization and the other as an alternating minimization scheme, both of which include first- and second-order variants. Both sets of algorithms have theoretical guarantees. In particular, for the alternating minimization, we establish global convergence and worst-case complexity bounds. Additionally, using the Kurdyka-Lojasiewicz property, we show that the alternating minimization converges to a unique limit point. We provide extensive numerical results for the recovery of union of subspaces and clustering under entry sampling and dense Gaussian sampling. Our methods are competitive with existing approaches and, in particular, high accuracy is achieved in the recovery using Riemannian second-order methods.

stat.ML↗