English
Related papers

Related papers: AdaMuon: Adaptive Muon Optimizer

200 papers

The alternating direction method of multipliers (ADMM) has been popular for solving many signal processing problems, convex or nonconvex. In this paper, we study an asynchronous implementation of the ADMM for solving a nonconvex nonsmooth…

Information Theory · Computer Science 2014-12-19 Mingyi Hong

Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Schedule-Free (SF) methods address this by removing explicit…

Machine Learning · Computer Science 2026-05-25 Anuj Apte , Pranav Deshpande , Niraj Kumar , Shouvanik Chakrabarti , Junhyung Lyle Kim

Autoregressive next-token training offers a unified formulation for image generation and text understanding, but it also creates strong modality competition that destabilizes optimization and limits large-batch scaling. We show that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Yishun Lu , Wes Armour

Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable…

Computer Vision and Pattern Recognition · Computer Science 2022-04-13 Yulin Wang , Yang Yue , Yuanze Lin , Haojun Jiang , Zihang Lai , Victor Kulikov , Nikita Orlov , Humphrey Shi , Gao Huang

Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. However, all current methods impose fixed LMO geometries for…

Artificial Intelligence · Computer Science 2026-05-20 Thomas Massena , Corentin Friedrich , Mathieu Serrurier

Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective way to steer language models (LMs) toward preferred behaviors using reward models (RM). However, these approaches can be…

Computation and Language · Computer Science 2026-03-16 Vinod Raman , Hilal Asi , Satyen Kale

We propose a Regularized Adaptive Momentum Dual Averaging (RAMDA) algorithm for training structured neural networks. Similar to existing regularized adaptive methods, the subproblem for computing the update direction of RAMDA involves a…

Machine Learning · Computer Science 2024-12-30 Zih-Syuan Huang , Ching-pei Lee

Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defining a learning rate schedule involves troublesome…

Machine Learning · Computer Science 2021-02-18 David Macêdo , Pedro Dreyer , Teresa Ludermir , Cleber Zanchettin

Parameter management is essential for distributed training of large machine learning (ML) tasks. Some ML tasks are hard to distribute because common approaches to parameter management can be highly inefficient. Advanced parameter management…

Machine Learning · Computer Science 2023-08-21 Alexander Renz-Wieland , Andreas Kieslinger , Robert Gericke , Rainer Gemulla , Zoi Kaoudi , Volker Markl

Multi-Task Learning (MTL) is a foundational machine learning problem that has seen extensive development over the past decade. Recently, various optimization-based MTL approaches have been proposed to learn multiple tasks simultaneously by…

Machine Learning · Computer Science 2026-04-13 Zhipeng Zhou , Linxiao Cao , Pengcheng Wu , Peilin Zhao , Chunyan Miao

The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Feiyang Kang , Nadine Chang , Maying Shen , Marc T. Law , Rafid Mahmood , Ruoxi Jia , Jose M. Alvarez

Adaptive gradient methods like Adagrad and its variants are widespread in large-scale optimization. However, their use of diagonal preconditioning matrices limits the ability to capture parameter correlations. Full-matrix adaptive methods,…

Machine Learning · Computer Science 2025-09-01 Tatyana Matveeva , Aleksandr Katrutsa , Evgeny Frolov

In recent years, Muon has emerged as the dominant method for training large language models, and transformers more broadly. The essential difference, when compared to standard gradient descent methods, is to replace the usual update matrix…

Machine Learning · Computer Science 2026-05-25 Fangzhou Wu , Rikhav Shah , Sandeep Silwal , Qiuyi Zhang

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

Mix-up is a key technique for consistency regularization-based semi-supervised learning methods, blending two or more images to generate strong-perturbed samples for strong-weak pseudo supervision. Existing mix-up operations are performed…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Zhiqiang Shen , Peng Cao , Junming Su , Jinzhu Yang , Osmar R. Zaiane

Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Myunghun Jung , Hoirin Kim

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…

Machine Learning · Computer Science 2017-12-08 Chia-Yu Chen , Jungwook Choi , Daniel Brand , Ankur Agrawal , Wei Zhang , Kailash Gopalakrishnan

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Suorong Yang , Peijia Li , Xin Xiong , Furao Shen , Jian Zhao

Adaptive moment methods such as Adam use a diagonal, coordinate-wise preconditioner based on exponential moving averages of squared gradients. This diagonal scaling is coordinate-system dependent and can struggle with dense or rotated…

Machine Learning · Computer Science 2026-04-09 Devender Singh , Tarun Sheel

We introduce a novel algorithm for gradient-based optimization of stochastic objective functions. The method may be seen as a variant of SGD with momentum equipped with an adaptive learning rate automatically adjusted by an 'energy'…

Optimization and Control · Mathematics 2022-03-24 Hailiang Liu , Xuping Tian