English
Related papers

Related papers: How Muon's Spectral Design Benefits Generalization…

200 papers

Gradient orthogonalization is a simple strategy that shows great utility in speeding up gradient descent. The Muon optimizer (Jordan, Jin, et al., 2024) combines gradient orthogonalization with first-order momentum and achieves significant…

Machine Learning · Computer Science 2025-10-21 Ahmed Khaled , Kaan Ozkara , Tao Yu , Mingyi Hong , Youngsuk Park

Optimization methods play a central role in signal processing, serving as the mathematical foundation for inference, estimation, and control. While classical iterative optimization algorithms provide interpretability and theoretical…

Machine Learning · Computer Science 2026-04-01 Nir Shlezinger , Santiago Segarra , Yi Zhang , Dvir Avrahami , Zohar Davidov , Tirza Routtenberg , Yonina C. Eldar

With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the…

Machine Learning · Computer Science 2025-09-15 Xinyi Gao , Dongting Xie , Yihang Zhang , Zhengren Wang , Chong Chen , Conghui He , Hongzhi Yin , Wentao Zhang

Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during…

Computation and Language · Computer Science 2020-10-13 Inbar Oren , Jonathan Herzig , Nitish Gupta , Matt Gardner , Jonathan Berant

Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data. Toward addressing this challenge, we consider the domain generalization…

Machine Learning · Statistics 2021-11-16 Alexander Robey , George J. Pappas , Hamed Hassani

Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Yang Yang , Hongpeng Pan , Qing-Yuan Jiang , Yi Xu , Jinghui Tang

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

Muon orthogonalizes matrix updates, but multi-head attention naturally operates at the level of heads. This granularity mismatch raises the question of whether Muon should be applied to the full attention projection, to individual heads, or…

Machine Learning · Computer Science 2026-05-12 Hongtao Zhang , Wenjie Zhou , Wei Chen , Xueqi Cheng

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Akshit Achara , Ram Krishna Pandey

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance…

Machine Learning · Computer Science 2020-06-15 Kaixiong Zhou , Xiao Huang , Yuening Li , Daochen Zha , Rui Chen , Xia Hu

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

The graph neural network (GNN) has demonstrated its superior performance in various applications. The working mechanism behind it, however, remains mysterious. GNN models are designed to learn effective representations for graph-structured…

Machine Learning · Computer Science 2022-06-10 Zepeng Zhang , Ziping Zhao

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…

Machine Learning · Computer Science 2019-10-14 Yeounoh Chung , Peter J. Haas , Eli Upfal , Tim Kraska

Many current neural networks for medical imaging generalise poorly to data unseen during training. Such behaviour can be caused by networks overfitting easy-to-learn, or statistically dominant, features while disregarding other potentially…

Image and Video Processing · Electrical Eng. & Systems 2022-12-05 Joona Pohjonen , Carolin Stürenberg , Antti Rannikko , Tuomas Mirtti , Esa Pitkänen

Real-world datasets are inherently heterogeneous, yet how per-class structural differences and sampling imbalance shape the training dynamics of diffusion models-and potentially exacerbate disparities-remains poorly understood. While models…

Machine Learning · Statistics 2026-05-08 Flavio Nicoletti , Chenxiao Ma , Enrico Ventura , Luca Saglietti , Stefano Sarao Mannelli

Domain generalization (DG) aims to incorporate knowledge from multiple source domains into a single model that could generalize well on unseen target domains. This problem is ubiquitous in practice since the distributions of the target data…

Machine Learning · Statistics 2019-07-26 Shoubo Hu , Kun Zhang , Zhitang Chen , Laiwan Chan

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize to unseen…

Computation and Language · Computer Science 2024-10-21 Dylan Zhang , Justin Wang , Francois Charton

Muon is a matrix-aware optimizer that leverages Newton-Schulz (NS) iterations to enforce spectral gradient orthogonalization by driving all singular values of the momentum matrix toward 1. While this uniform spectral whitening enhances…

Machine Learning · Computer Science 2026-05-20 Chongyu Fan , Gaowen Liu , Mingyi Hong , Ramana Rao Kompella , Sijia Liu

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…

Machine Learning · Computer Science 2026-05-11 Junjie Yu , Yue Wang , Zihan Deng , Yan Zhu , Wenxiao Ma , Quanying Liu

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