The paper presents a framework for retraction-based convex optimization on Riemannian manifolds, introducing retraction-specific convex sets and retraction-based gradient projection algorithms. It extends the standard theory of gradient projection algorithms to this setting and proves convergence results for various stepsize rules. The authors apply the framework to weighted low-rank approximation and validate the convergence results numerically on an image completion task.
arXiv:2510. 21033v3 Announce Type: replace-cross Abstract: We develop a theory of iso-Riemannian optimization for problems constrained to learned data manifolds, a setting in which classical Riemannian optimization - and Riemannian gradient descent in particular - can be poorly suited.
arXiv:2607. 09546v1 Announce Type: new Abstract: We address the low-rank matrix completion problem by incorporating graph regularization into the existing Riemannian Trust-Region Matrix Completion (RTRMC) framework.
arXiv:2503. 24075v4 Announce Type: replace-cross Abstract: Low-rank optimization problems with sparse simplex constraints involve variables that must satisfy nonnegativity, sparsity, and sum-to-1 conditions, making their optimization particularly challenging due to the interplay between low-rank structures and constraints.
arXiv:2606. 12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent updates that require careful hyperparameter tuning and ignore the optimization landscape's curvature.
arXiv:2510. 09468v3 Announce Type: replace Abstract: Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective.
arXiv:2608. 02576v1 Announce Type: new Abstract: We consider optimization problems defined on product spaces of simplices.
arXiv:2606. 00413v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) makes high-dimensional regression tractable by projecting the covariates onto a low-dimensional subspace that preserves the conditional mean of the response.
arXiv:2608.29507v1 Announce Type: cross Abstract: Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-spec...
The paper investigates how training data limits the geometry of an optimizer through the covectors that a specified information channel can observe. It establishes that, under affine‑invariant Riemannian geometry, a full‑column‑rank positive‑definite compression can be uniquely completed via a split‑Hadamard metric submetry, yielding exact variational reduction from the full geometry to the visible target. The resulting framework provides explicit formulas for pullback metrics, Gram matrices, and prior‑data shrinkage, and characterizes the gauge‑invariant rank stratification of the positive‑definite cone as the channel varies.
arXiv:2509. 07779v2 Announce Type: replace-cross Abstract: We study decentralized online Riemannian optimization over manifolds with possibly positive curvature, going beyond the Hadamard manifold setting.
arXiv:2607. 25299v1 Announce Type: cross Abstract: Optimization over the Stiefel manifold plays a significant role in various machine learning tasks.
arXiv:2607. 22004v1 Announce Type: new Abstract: Energy natural gradient descent (ENGD) aligns parameter updates with the curvature of an underlying function-space energy, but existing formulations assume an unconstrained Euclidean parameter domain.