English
Related papers

Related papers: Delving into Muon and Beyond: Deep Analysis and Ex…

200 papers

Permutation synchronization is an important problem in computer science that constitutes the key step of many computer vision tasks. The goal is to recover $n$ latent permutations from their noisy and incomplete pairwise measurements. In…

Statistics Theory · Mathematics 2024-05-13 Duc Nguyen , Anderson Ye Zhang

Muons have a similar latency/energy correlation from pion decay as do the neutrinos, and hence in each time-slice in a stroboscopic analysis measurements of their momentum spectra can reduce systematic uncertainties due to flux. There are,…

High Energy Physics - Experiment · Physics 2022-12-20 Henry J. Frisch

We identify and formalize an underexplored phenomenon in deep learning optimization: directional alignment and loss convergence can be decoupled. An optimizer can exhibit near-perfect directional consistency (cc_t -> 1, measured via…

Machine Learning · Computer Science 2026-05-08 Victor Daniel Gera

The ADAM optimizer is exceedingly popular in the deep learning community. Often it works very well, sometimes it doesn't. Why? We interpret ADAM as a combination of two aspects: for each weight, the update direction is determined by the…

Machine Learning · Computer Science 2020-12-15 Lukas Balles , Philipp Hennig

We study the implicit bias of momentum-based optimizers on smooth homogeneous models. We show that \textit{momentum steepest descent} algorithms like Muon (spectral norm), MomentumGD ($\ell_2$ norm), and Signum ($\ell_\infty$ norm) are…

Machine Learning · Computer Science 2026-05-26 Eitan Gronich , Gal Vardi

We introduce a new paradigm for solving regularized variational problems. These are typically formulated to address ill-posed inverse problems encountered in signal and image processing. The objective function is traditionally defined by…

Optimization and Control · Mathematics 2021-04-22 Jean-Christophe Pesquet , Audrey Repetti , Matthieu Terris , Yves Wiaux

Adam-type algorithms have become a preferred choice for optimisation in the deep learning setting, however, despite success, their convergence is still not well understood. To this end, we introduce a unified framework for Adam-type…

Machine Learning · Computer Science 2024-09-24 Yiming Jiang , Jinlan Liu , Dongpo Xu , Danilo P. Mandic

Optimal modulation (OM) schemes for Gaussian channels with peak and average power constraints are known to require nonuniform probability distributions over signal points, which presents practical challenges. An established way to map…

Information Theory · Computer Science 2022-11-01 Basak Ozaydin , Muriel Médard , Ken Duffy

Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite their empirical success, the reasons behind Adam's superior performance over SGD remain poorly…

Machine Learning · Computer Science 2026-02-19 Akiyoshi Tomihari , Issei Sato

Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view since it may not…

Machine Learning · Computer Science 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new optimizer: Perturbated Unit Gradient Descent (PUGD) algorithm…

Machine Learning · Computer Science 2022-11-10 Ching-Hsun. Tseng , Liu-Hsueh. Cheng , Shin-Jye. Lee , Xiaojun Zeng

Atomistic foundation models constitute a paradigm shift in computational materials science by providing universal machine-learned interatomic potentials with broad transferability across chemical spaces. Although fine-tuning is essential…

Computational Physics · Physics 2025-12-08 Xiaoqing Liu , Yangshuai Wang , Teng Zhao

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

Fully decentralized Muon is difficult because its nonlinear matrix-sign operator does not commute with linear gossip averaging. This makes decentralized Muon a structural design problem: in designing the algorithm, one must distinguish…

Optimization and Control · Mathematics 2026-04-28 Hengrui Zhang , Boao Kong , Jiahe Geng , Zhengyang Huang

The residual update of a pre-norm Transformer layer admits an interpretation as one step of a first-order optimizer acting on a surrogate token energy, wherein the attention and MLP sublayers function as gradient oracles. Based on this…

Machine Learning · Computer Science 2026-05-26 Jingchu Gai , Nai-Chieh Huang , Jiayun Wu

Equivariant neural networks encode geometric symmetries by construction, yet they are often difficult to optimize and can underperform less constrained architectures. A growing body of work addresses this through architectural modifications…

Machine Learning · Computer Science 2026-05-28 Teodor-Mihai Stupariu , Andrei Manolache

In the training of neural networks, adaptive moment estimation (Adam) typically converges fast but exhibits suboptimal generalization performance. A widely accepted explanation for its defect in generalization is that it often tends to…

Machine Learning · Computer Science 2026-03-10 Tao Shi , Liangming Chen , Long Jin , Mengchu Zhou

Bayesian inference, while foundational to probabilistic reasoning, is often hampered by the computational intractability of posterior distributions, particularly through the challenging evidence integral. Conventional approaches like Markov…

Machine Learning · Computer Science 2025-11-11 Di Zhang

Adaptive Moment Estimation (Adam) is a cornerstone optimization algorithm in deep learning, widely recognized for its flexibility with adaptive learning rates and efficiency in handling large-scale data. However, despite its practical…

Machine Learning · Computer Science 2025-05-21 Ruinan Jin , Xiao Li , Yaoliang Yu , Baoxiang Wang

Beside the standard stochastic gradient descent (SGD) method, the Adam optimizer due to Kingma & Ba (2014) is currently probably the best-known optimization method for the training of deep neural networks in artificial intelligence (AI)…

Optimization and Control · Mathematics 2025-11-11 Steffen Dereich , Thang Do , Arnulf Jentzen , Philippe von Wurstemberger