English
Related papers

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

200 papers

In this paper we address the convergence of stochastic approximation when the functions to be minimized are not convex and nonsmooth. We show that the "mean-limit" approach to the convergence which leads, for smooth problems, to the ODE…

Optimization and Control · Mathematics 2018-05-08 Szymon Majewski , Błażej Miasojedow , Eric Moulines

The recent empirical success of the Muon optimizer has renewed interest in non-Euclidean optimization, typically justified by similarities with second-order methods, and linear minimization oracle (LMO) theory. In this paper, we challenge…

In this paper, we propose a unified convergence analysis for a class of generic shuffling-type gradient methods for solving finite-sum optimization problems. Our analysis works with any sampling without replacement strategy and covers many…

Optimization and Control · Mathematics 2021-09-21 Lam M. Nguyen , Quoc Tran-Dinh , Dzung T. Phan , Phuong Ha Nguyen , Marten van Dijk

With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention. Several implementations favor the use of Conjugate Gradient (CG) and…

Machine Learning · Computer Science 2020-03-02 Buse Melis Ozyildirim , Mariam Kiran

In this article we propose a method for solving unconstrained optimization problems with convex and Lipschitz continuous objective functions. By making use of the Moreau envelopes of the functions occurring in the objective, we smooth the…

Optimization and Control · Mathematics 2012-07-16 Radu Ioan Bot , Christopher Hendrich

This note clarifies some confusions (and perhaps throws out more) around model-based reinforcement learning and their theoretical understanding in the context of deep RL. Main topics of discussion are (1) how to reconcile model-based RL's…

Machine Learning · Computer Science 2024-04-16 Nan Jiang

Deep learning models require a large amount of data to perform well. When data is scarce for a target task, we can transfer the knowledge gained by training on similar tasks to quickly learn the target. A successful approach is…

Machine Learning · Computer Science 2021-03-18 Alberto Bernacchia

ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically.…

Machine Learning · Computer Science 2019-01-28 Jiancheng Lyu , Shuai Zhang , Yingyong Qi , Jack Xin

The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become…

Machine Learning · Computer Science 2026-05-27 Jiacheng Li , Jianchao Tan , Hongtao Xu , Jiaqi Zhang , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai

Muon has recently emerged as a strong alternative to AdamW for training neural networks, with encouraging large-scale pretraining results and growing evidence that matrix-structured updates can be faster in practice. Yet Muon, and more…

Machine Learning · Computer Science 2026-05-19 Abdurakhmon Sadiev , Artavazd Maranjyan , Ivan Ilin , Peter Richtárik

Non-convex optimization is a critical tool in advancing machine learning, especially for complex models like deep neural networks and support vector machines. Despite challenges such as multiple local minima and saddle points, non-convex…

Machine Learning · Computer Science 2024-10-04 Greg B Fotopoulos , Paul Popovich , Nicholas Hall Papadopoulos

In this work, we develop proximal preconditioned gradient methods with a focus on spectral gradient methods providing a proximal extension to the Muon and Scion optimizers. We introduce a family of stochastic algorithms that can handle a…

In binary classification and regression problems, it is well understood that Lipschitz continuity and smoothness of the loss function play key roles in governing generalization error bounds for empirical risk minimization algorithms. In…

Machine Learning · Computer Science 2016-09-14 Ambuj Tewari , Sougata Chaudhuri

We consider deep neural networks with a Lipschitz continuous activation function and with weight matrices of variable widths. We establish a uniform convergence analysis framework in which sufficient conditions on weight matrices and bias…

Machine Learning · Computer Science 2023-06-05 Yuesheng Xu , Haizhang Zhang

We propose a new family of adaptive first-order methods for a class of convex minimization problems that may fail to be Lipschitz continuous or smooth in the standard sense. Specifically, motivated by a recent flurry of activity on…

Optimization and Control · Mathematics 2021-07-19 Kimon Antonakopoulos , Panayotis Mertikopoulos

How well do representations learned by ML models align with those of humans? Here, we consider concept representations learned by deep learning models and evaluate whether they show a fundamental behavioral signature of human concepts, the…

Artificial Intelligence · Computer Science 2024-05-28 Siddhartha K. Vemuri , Raj Sanjay Shah , Sashank Varma

The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperformed convex ones.…

Optimization and Control · Mathematics 2017-02-14 Quanming Yao , James. T Kwok

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Machine Learning · Computer Science 2025-10-28 Wenju Sun , Qingyong Li , Wen Wang , Yang Liu , Yangli-ao Geng , Boyang Li

Constrained optimization problems where both the objective and constraints may be nonsmooth and nonconvex arise across many learning and data science settings. In this paper, we show for any Lipschitz, weakly convex objectives and…

Optimization and Control · Mathematics 2025-01-17 Zhichao Jia , Benjamin Grimmer

In this paper we propose a variant of the random coordinate descent method for solving linearly constrained convex optimization problems with composite objective functions. If the smooth part of the objective function has Lipschitz…

Optimization and Control · Mathematics 2013-02-14 Ion Necoara , Andrei Patrascu