Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization

• URL: http://arxiv.org/abs/2608.26288v1
• Date: Wed, 26 Aug 2026 18:14:00 GMT
• Title: Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization
• Abstract summary: We show that finite Newton-Schulz iteration can be beneficial for nonsmooth non optimization.<n>The argument extends beyond Newton-Schulz to general spectral maps of the same property.
• Score: 12.70261661948628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Muon has emerged as a strong optimizer for the matrix-valued parameters in large language model pretraining, approximately orthogonalizing its momentum with a few Newton-Schulz iterations. Existing theory either replaces this iteration with the exact polar factor it approximates, or treats its finite depth as an approximation error, and thus the iteration Muon actually runs can only hurt the guarantees. We show that finite Newton-Schulz can instead be beneficial for nonsmooth nonconvex optimization. To this end, we analyze Muon through the online-to-nonconvex conversion, which views the update rule as an online learner and converts its regret bound into a stationarity guarantee. The finite Newton-Schulz iteration smooths the discontinuous polar map into a Lipschitz map of the singular values, and Muon with finite Newton-Schulz can be regarded as an online learner with a smoothed spectral potential. This smoothing is exactly what the conversion needs: we prove that a Newton-Schulz depth growing only logarithmically in the target accuracy suffices for convergence to stationary points in nonsmooth nonconvex optimization, whereas Muon with the exact-polar update may fail to converge. The resulting sample complexity bounds match the best-known guarantees for nonsmooth nonconvex optimization and are optimal for smooth nonconvex optimization up to problem-dependent factors. The argument extends beyond Newton-Schulz to general spectral maps with the same smoothing property.

Related papers

• Nonsmooth Optimization via Orthogonalized Momentum [11.546795991978613]
  We show that for every fixed momentum factor $in[0,1)$, Muon can fail to approach the global optimal solution a convex Lipschitz objective.<n>We propose MAGD, which combines momentum with gradient, weighted based on their relative progress.
  arXiv  Detail & Related papers  (2026-09-12T03:08:36Z)
• OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality [23.28384210732827]
  We show that closed-loop scalar momentum.<n>optimization can be combined with Muon-style momentum.<n>optimization while retaining noise adaptivity and zero-noise optimality up to logarithmic factors.<n>These results show that OptMuon-A achieves the noise-rate.<n>(tildemathcal O(T-1/2+1/2T--1/2)) under average smoothness, while OptMuon-I achieves the noise-rate.<n>(tildemathcal O(T-1/2+
  arXiv  Detail & Related papers  (2026-06-07T18:59:24Z)
• Muon is Not That Special: Random or Inverted Spectra Work Just as Well [50.969177887027115]
  We demonstrate that precise geometric structure is not key factor affecting performance.<n>We introduce Freon, a family of geometrics based on Schatten (quasi-size)norms.<n>We also introduce Kaon, an absurd that replaces singular values with random noise.
  arXiv  Detail & Related papers  (2026-05-11T19:42:48Z)
• Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition [11.258577546422295]
  We develop a theory for inexact polar decomposition in non$ matrix optimization undertailed noise.<n>We analyze a randomized low-rank polar decomposition that is substantially more efficient than fullspace methods.
  arXiv  Detail & Related papers  (2026-05-07T19:32:39Z)
• Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning [72.62839712454196]
  Recent advances in spectral optimization, notably Muon, have demonstrated that constraining update steps to the Stiefel manifold can significantly accelerate training and improveimation.<n>We argue that this "egalitarian" constraint is suboptimal for Deep Neural Networks, where the curvature spectrum is known to be highly heavy-tailed and ill-conditioned.<n>We propose textbfMousse (textbfMuon textbfOptimization textbfUtilizing textbfShampoo's textbfStruct
  arXiv  Detail & Related papers  (2026-03-10T14:03:49Z)
• UNSO: Unified Newton Schulz Orthogonalization [10.113387496783007]
  The Newton-Schulz (NS) has gained increasing interest for its role in the Muon and Stiefel manifold.<n>We consolidate the iterative structure into a unified framework, named Unified Newton-Schulz Orthogonalization (UNSO)<n>These learnable coefficients are then optimized, and achieve an outstanding performance with stable convergence.
  arXiv  Detail & Related papers  (2026-01-18T17:54:43Z)
• Beyond the Ideal: Analyzing the Inexact Muon Update [54.70108543057578]
  We show first analysis of the inexactized update at Muon's core.<n>We reveal a fundamental coupling between this inexactness and the optimal step size and momentum.
  arXiv  Detail & Related papers  (2025-10-22T18:01:07Z)
• Error Feedback for Muon and Friends [80.90330715662961]
  We introduce EF21-Muon, the first communication-efficient, non-Euclidean LMO-based with rigorous convergence guarantees.<n>Our theory covers non-Euclidean smooth and the more general $(L0, L1)$-smooth setting, matching best-known Euclidean rates and enabling faster convergence under suitable norm choices.
  arXiv  Detail & Related papers  (2025-10-01T08:20:08Z)
• Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update [88.73437209862891]
  In second-order optimization, a potential bottleneck can be computing the Hessian matrix of the optimized function at every iteration. We show that the Gaussian sketching matrix can be drastically sparsified, significantly reducing the computational cost of sketching. We prove that Newton-LESS enjoys nearly the same problem-independent local convergence rate as Gaussian embeddings.
  arXiv  Detail & Related papers  (2021-07-15T17:33:05Z)
• Oracle Complexity in Nonsmooth Nonconvex Optimization [49.088972349825085]
  It is well-known that given a smooth, bounded-from-below $$stationary points, Oracle-based methods can find smooth approximation of smoothness. In this paper, we prove an inherent trade-off between optimization and smoothing dimension.
  arXiv  Detail & Related papers  (2021-04-14T10:42:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.