paper-with-me

Papers

Muon on the Stiefel Manifold Admits an Exact Closed-Form Update

2026-08-06 · Mikhail Solonko, Molozhavenko Alexander, Maxim Rakhuba arxiv

We study Muon, a recently proposed matrix-aware optimization method, in the context of the Stiefel manifold. This manifold consists of matrices with orthonormal columns and is ubiquitous in machine learning and scientific computing. Existing extensions of Muon to this manifold rely on heuristic, approximate, or iterative updates with varying computational efficiency. We show that the corresponding Stiefel Muon update admits an exact closed-form solution and use this result to develop Skewon, a practical algorithm for orthogonality-constrained optimization with an efficient implementation. We further establish first-order convergence guarantees for Skewon in the smooth non-convex setting.

📄 PDF Abstract BibTeX arXiv:2608.06218

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds

2026-05-10 · Yibang Li, Bihari Lal Pandey, Ravi Sah, Andi Han 외 arxiv

Muon and related norm-constrained matrix optimizers have become central to large-scale learning problems. They are formulated as a linear maximization oracle (LMO) over an ambient matrix-norm ball in unconstrained Euclid…

Image Classification

Manifold constrained steepest descent for smooth and closed-set optimization

2026-01-29 · Kaiwei Yang, Lexiao Lai arxiv

We study minimization of smooth functions over feasible sets that have smooth embedded-manifold structure throughout or only on selected regions, using linear minimization oracles (LMOs) to determine search directions un…

Muon Converges under Heavy-Tailed Noise: Nonconvex Hölder-Smooth Empirical Risk Minimization

2026-03-16 · Hideaki Iiduka arxiv

Muon is a recently proposed optimizer that enforces orthogonality in parameter updates by projecting gradients onto the Stiefel manifold, leading to stable and efficient training in large-scale deep neural networks. Mean…

ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum

2026-07-05 · Haiwen Yi, Xinyuan Song arxiv

Orthogonal and Stiefel layers give neural weights exact spectral control, but they also impose a strong modeling constraint: all represented singular values are fixed at one. Many settings that benefit from an orthonorma…

Closed-form geodesics and trust-region method to calculate Riemannian logarithms on Stiefel and its quotient manifolds

2021-03-12 · Du Nguyen

We provide two closed-form geodesic formulas for a family of metrics on Stiefel manifold, parameterized by two positive numbers, having both the embedded and canonical metrics as special cases. The closed-form formulas a…

Form