Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.06884 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911660853166080 |
|---|---|
| author | Choudhury, Sayantan Cheng, Xiaoran Takáč, Martin Na, Sen Kolar, Mladen |
| author_facet | Choudhury, Sayantan Cheng, Xiaoran Takáč, Martin Na, Sen Kolar, Mladen |
| contents | Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muon addresses this mismatch by updating along the polar factor of a momentum matrix, but its theoretical understanding has lagged behind practice. In particular, practical implementations incorporate Nesterov momentum, compute the polar factor only approximately, and operate with stochastic gradients that may be heavy-tailed. We close this gap by developing a convergence theory for Muon with Nesterov momentum and inexact polar decomposition in non-convex matrix optimization under heavy-tailed noise. Our analysis builds on a unified framework for inexact polar decomposition that captures practical iterative approximations such as Newton-Schulz and quantifies how their errors propagate through the optimization dynamics. Under this framework, we establish an optimal iteration and sample complexity of $O \left(\varepsilon^{\frac{-(3α-2)}{(α-1)}} \right)$ for finding an $\varepsilon$-stationary point, where $α\in(1,2]$ denotes the heavy-tail index. For the inexact-polar setting with $σ_1=0$, we also provide guarantees that do not require prior knowledge of $α$. We analyze a randomized low-rank polar decomposition that is substantially more efficient than full-space methods while remaining compatible with our theory. Numerical experiments further demonstrate the effectiveness of the proposed inexact and randomized variants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06884 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition Choudhury, Sayantan Cheng, Xiaoran Takáč, Martin Na, Sen Kolar, Mladen Optimization and Control Machine Learning Most first-order optimizers treat matrix-valued parameters as vectors, ignoring the intrinsic geometry of hidden-layer weights in neural networks. Muon addresses this mismatch by updating along the polar factor of a momentum matrix, but its theoretical understanding has lagged behind practice. In particular, practical implementations incorporate Nesterov momentum, compute the polar factor only approximately, and operate with stochastic gradients that may be heavy-tailed. We close this gap by developing a convergence theory for Muon with Nesterov momentum and inexact polar decomposition in non-convex matrix optimization under heavy-tailed noise. Our analysis builds on a unified framework for inexact polar decomposition that captures practical iterative approximations such as Newton-Schulz and quantifies how their errors propagate through the optimization dynamics. Under this framework, we establish an optimal iteration and sample complexity of $O \left(\varepsilon^{\frac{-(3α-2)}{(α-1)}} \right)$ for finding an $\varepsilon$-stationary point, where $α\in(1,2]$ denotes the heavy-tail index. For the inexact-polar setting with $σ_1=0$, we also provide guarantees that do not require prior knowledge of $α$. We analyze a randomized low-rank polar decomposition that is substantially more efficient than full-space methods while remaining compatible with our theory. Numerical experiments further demonstrate the effectiveness of the proposed inexact and randomized variants. |
| title | Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2605.06884 |