English
Related papers

Related papers: Muon Does Not Converge on Convex Lipschitz Functio…

200 papers

In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on isolated, aggregate performance analyses, overlooking important…

Machine Learning · Computer Science 2020-08-12 Megha Srivastava , Besmira Nushi , Ece Kamar , Shital Shah , Eric Horvitz

Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness…

Optimization and Control · Mathematics 2024-12-30 Eduard Gorbunov , Nazarii Tupitsa , Sayantan Choudhury , Alen Aliev , Peter Richtárik , Samuel Horváth , Martin Takáč

The standard assumption for proving linear convergence of first order methods for smooth convex optimization is the strong convexity of the objective function, an assumption which does not hold for many practical applications. In this…

Optimization and Control · Mathematics 2016-08-10 I. Necoara , Yu. Nesterov , F. Glineur

We focus on nonconvex and nonsmooth minimization problems with a composite objective, where the differentiable part of the objective is freed from the usual and restrictive global Lipschitz gradient continuity assumption. This longstanding…

Optimization and Control · Mathematics 2017-06-21 Jérôme Bolte , Shoham Sabach , Marc Teboulle , Yakov Vaisbourd

Recent advances in spectral optimization, notably Muon, have demonstrated that constraining update steps to the Stiefel manifold can significantly accelerate training and improve generalization. However, Muon implicitly assumes an isotropic…

Machine Learning · Computer Science 2026-04-02 Yechen Zhang , Shuhao Xing , Junhao Huang , Kai Lv , Yunhua Zhou , Xipeng Qiu , Qipeng Guo , Kai Chen

In this paper, we introduce a model for analyzing deep learning optimization over a single iteration by leveraging the matrix structure of the weights. We derive the model by assuming isotropy of curvature, including the second-order…

Optimization and Control · Mathematics 2025-11-04 Weijie Su

Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Muon built on a simple…

Machine Learning · Computer Science 2026-05-11 Yuxuan Lou , Yang You

We present a comprehensive theoretical and empirical study of the Muon optimizer for training transformers only with a small to medium decoder (30M - 200M parameters), with an emphasis on its mathematical foundations, convergence properties…

Machine Learning · Computer Science 2025-09-30 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

Various optimal gradient-based algorithms have been developed for smooth nonconvex optimization. However, many nonconvex machine learning problems do not belong to the class of smooth functions and therefore the existing algorithms are…

Optimization and Control · Mathematics 2023-06-27 Ziyi Chen , Yi Zhou , Yingbin Liang , Zhaosong Lu

Large learning rates, when applied to gradient descent for nonconvex optimization, yield various implicit biases including the edge of stability (Cohen et al., 2021), balancing (Wang et al., 2022), and catapult (Lewkowycz et al., 2020).…

Machine Learning · Computer Science 2023-12-13 Yuqing Wang , Zhenghao Xu , Tuo Zhao , Molei Tao

Deep learning has been applied to various tasks in the field of machine learning and has shown superiority to other common procedures such as kernel methods. To provide a better theoretical understanding of the reasons for its success, we…

Machine Learning · Statistics 2023-05-31 Satoshi Hayakawa , Taiji Suzuki

This paper is devoted to a new modification of a recently proposed adaptive stochastic mirror descent algorithm for constrained convex optimization problems in the case of several convex functional constraints. Algorithms, standard and its…

Optimization and Control · Mathematics 2020-01-22 Mohammad S. Alkousa

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Yuncheng Yang , Chuyan Zhang , Zuopeng Yang , Yuting Gao , Yulei Qin , Ke Li , Xing Sun , Jie Yang , Yun Gu

Neural network (NN) training is inherently a large-scale matrix optimization problem, yet the matrix structure of NN parameters has long been overlooked. Recently, the optimizer Muon \citep{jordanmuon}, which explicitly exploits this…

Machine Learning · Computer Science 2026-04-21 Chuan He , Zhanwang Deng , Zhaosong Lu

This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on its convergence rate. The approach extends max-affine methods from convex shape-restricted…

Machine Learning · Statistics 2025-11-20 Gábor Balázs

Integrally convex functions constitute a fundamental function class in discrete convex analysis, including M-convex functions, L-convex functions, and many others. This paper aims at a rather comprehensive survey of recent results on…

Combinatorics · Mathematics 2023-02-23 Kazuo Murota , Akihisa Tamura

The Muon optimizer, a matrix-structured algorithm that leverages spectral orthogonalization of gradients, is a milestone in the pretraining of large language models. However, the underlying mechanisms of Muon -- particularly the role of…

Machine Learning · Computer Science 2026-01-21 Jianhao Ma , Yu Huang , Yuejie Chi , Yuxin Chen

Optimization with matrix gradient orthogonalization has recently demonstrated impressive results in the training of deep neural networks (Jordan et al., 2024; Liu et al., 2025). In this paper, we provide a theoretical analysis of this…

Machine Learning · Computer Science 2025-04-09 Dmitry Kovalev

Min-max problems have broad applications in machine learning, including learning with non-decomposable loss and learning with robustness to data distribution. Convex-concave min-max problem is an active topic of research with efficient…

Optimization and Control · Mathematics 2021-05-12 Hassan Rafique , Mingrui Liu , Qihang Lin , Tianbao Yang

Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the…

Machine Learning · Computer Science 2026-05-25 Tianyu Pang , Yujie Fang , Zihang Liu , Shenyang Deng , Lei Hsiung , Shuhua Yu , Yaoqing Yang
‹ Prev 1 3 4 5 6 7 10 Next ›