Nonsmooth Optimization via Orthogonalized Momentum

• URL: http://arxiv.org/abs/2609.13677v1
• Date: Sat, 12 Sep 2026 03:08:36 GMT
• Title: Nonsmooth Optimization via Orthogonalized Momentum
• Abstract summary: 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.
• Score: 11.546795991978613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern real application problems involve matrix-valued parameters, yet conventional optimizers treat them as vectors, thereby motivating matrix-aware methods that exploit input-output geometry, such as Muon which orthogonalizes the momentum matrices before parameter updates. Its empirical success raises a conceptual question: can orthogonalized momentum remain effective beyond smooth optimization? This paper studies this question for locally Lipschitz functions using a generalized derivative framework compatible with backpropagation. Our first contribution is to identify a key limitation: for every fixed momentum factor $β\in[0,1)$, Muon can fail to approach the global optimal solution of a convex Lipschitz objective from almost every initialization, when step sizes adapt to the full gradient history. The failure can occur even along bounded iterates. Our example is inspired by the one of Parshakova et al. which only covers $β\in[0,\frac{1}{2})$. Then, we show that the obstruction lies in fixed momentum rather than orthogonalization. Indeed, when the momentum factor is adaptive and approaches 1 together with a vanishing step size, Muon recovers asymptotic convergence for nonconvex nonsmooth optimization under the boundedness and regularity conditions. Moreover, we propose MAGD, which combines orthogonalized momentum with gradient, weighted based on their relative progress. MAGD retains asymptotic convergence in nonconvex settings and achieves an $O(\min\{m,n\}ε^{-2})$ rate in convex settings. A lower bound shows the optimal dimension dependence. Experiments on synthetic problems, image classification, and LLM pretraining show MAGD is a simple and practical alternative to Muon. Together, our results characterize when orthogonalized momentum fails without smoothness and how it can be made reliable and we hope that the analysis may be useful more broadly.

Related papers

• Muse: Representation Geometry of Muon Beyond Normalized Momentum [26.90642116529718]
  Muon-styles apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before curvatureization.<n>We introduce method, a family of Muon-styles that shares the same momentum rule and Newton's momentum rule.<n>We show that balanced non-native representations can match the native representation, whereas reducing the shorter dimension weakens the scaling and singular-channel support, leading to behavior that increasingly normalized momentum.
  arXiv  Detail & Related papers  (2026-07-16T03:42:21Z)
• 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)
• Negative Momentum for Convex-Concave Optimization [7.509121810863555]
  This paper revisits momentum in the context of min-max optimization.<n>Momentum is a celebrated mechanism for accelerating dynamics in settings like convex minimization.<n>We show that negative momentum enables convergence significantly faster and more generally than known possible.
  arXiv  Detail & Related papers  (2026-04-18T20:55:49Z)
• Preconditioning Benefits of Spectral Orthogonalization in Muon [50.62925024212989]
  We study the effectiveness of a simplified variant of Muon in two case studies: matrix factorization and in-context learning of linear transformers.<n>Our analysis reveals that the Muon dynamics decouple into a collection of independent scalar sequences in the spectral domain, each exhibiting similar convergence behavior.
  arXiv  Detail & Related papers  (2026-01-20T00:08:31Z)
• Inertial Quadratic Majorization Minimization with Application to Kernel Regularized Learning [1.0282274843007797]
  We introduce the Quadratic Majorization Minimization with Extrapolation (QMME) framework and establish its sequential convergence properties.<n>To demonstrate practical advantages, we apply QMME to large-scale kernel regularized learning problems.
  arXiv  Detail & Related papers  (2025-07-06T05:17:28Z)
• Directional Smoothness and Gradient Methods: Convergence and Adaptivity [16.779513676120096]
  We develop new sub-optimality bounds for gradient descent that depend on the conditioning of the objective along the path of optimization.<n>Key to our proofs is directional smoothness, a measure of gradient variation that we use to develop upper-bounds on the objective.<n>We prove that the Polyak step-size and normalized GD obtain fast, path-dependent rates despite using no knowledge of the directional smoothness.
  arXiv  Detail & Related papers  (2024-03-06T22:24:05Z)
• ELRA: Exponential learning rate adaption gradient descent optimization method [83.88591755871734]
  We present a novel, fast (exponential rate), ab initio (hyper-free) gradient based adaption. The main idea of the method is to adapt the $alpha by situational awareness. It can be applied to problems of any dimensions n and scales only linearly.
  arXiv  Detail & Related papers  (2023-09-12T14:36:13Z)
• Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization [88.0031283949404]
  Many real-world problems have complicated non functional constraints and use a large number of data points. Our proposed method outperforms an existing method with the previously best-known result.
  arXiv  Detail & Related papers  (2022-12-19T14:48:54Z)
• Softmax-free Linear Transformers [90.83157268265654]
  Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. Existing methods are either theoretically flawed or empirically ineffective for visual recognition. We propose a family of Softmax-Free Transformers (SOFT)
  arXiv  Detail & Related papers  (2022-07-05T03:08:27Z)
• Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization [116.89941263390769]
  We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $min_mathbfxmax_mathbfyF(mathbfx) + H(mathbfx,mathbfy)$, where one has access to first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$. We present a emphaccelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragrad
  arXiv  Detail & Related papers  (2022-06-17T06:10:20Z)
• Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning [90.8576971748142]
  We develop a novel surrogate that can be optimized by closed-form solutions. We exploit upperwise correlation for completion, and thus an adaptive correlation learning model.
  arXiv  Detail & Related papers  (2022-03-04T08:50:50Z)

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.