English
Related papers

Related papers: On the Width Scaling of Neural Optimizers Under Ma…

200 papers

The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underlying mechanisms and relationship to adaptive optimizers such…

Machine Learning · Computer Science 2026-02-05 Xianbiao Qi , Marco Chen , Jiaquan Ye , Yelin He , Rong Xiao

Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimization removes explicit schedules via iterate averaging, and Muon improves the update…

Machine Learning · Computer Science 2026-05-22 Jueun Kim , Baekrok Shin , Jihun Yun , Beomhan Baek , Minhak Song , Chulhee Yun

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly…

Social and Information Networks · Computer Science 2020-08-31 Shuo Yu , Feng Xia , Jin Xu , Zhikui Chen , Ivan Lee

The ever-growing scale of deep learning models and training data underscores the critical importance of efficient optimization methods. While preconditioned gradient methods such as Adam and AdamW are the de facto optimizers for training…

Optimization and Control · Mathematics 2026-02-06 Tim Tsz-Kit Lau , Qi Long , Weijie Su

A deep neural network is a parametrization of a multilayer mapping of signals in terms of many alternatively arranged linear and nonlinear transformations. The linear transformations, which are generally used in the fully connected as well…

Machine Learning · Computer Science 2020-07-01 Ze-Feng Gao , Song Cheng , Rong-Qiang He , Z. Y. Xie , Hui-Hai Zhao , Zhong-Yi Lu , Tao Xiang

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

We introduce a Normalized Convolutional Neural Layer, a novel approach to normalization in convolutional networks. Unlike conventional methods, this layer normalizes the rows of the im2col matrix during convolution, making it inherently…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Dongsuk Kim , Geonhee Lee , Myungjae Lee , Shin Uk Kang , Dongmin Kim

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations. In particular, we study…

Machine Learning · Computer Science 2021-01-01 Kaifeng Lyu , Jian Li

This paper introduces an optimal control framework to address the inverse problem using a learned regularizer, with applications in image reconstruction. We build upon the concept of Learnable Optimization Algorithms (LOA), which combine…

Optimization and Control · Mathematics 2024-09-04 Wanyu Bian

Amortized optimization accelerates the solution of related optimization problems by learning mappings that exploit shared structure across problem instances. We explore the use of Scale Equivariant Graph Metanetworks (ScaleGMNs) for this…

Artificial Intelligence · Computer Science 2025-10-10 Bart Kuipers , Freek Byrman , Daniel Uyterlinde , Alejandro García-Castellanos

Recently, model-driven deep learning unrolls a certain iterative algorithm of a regularization model into a cascade network by replacing the first-order information (i.e., (sub)gradient or proximal operator) of the regularizer with a…

Machine Learning · Computer Science 2021-12-24 Zhuo-Xu Cui , Jing Cheng , Qingyong Zhu , Yuanyuan Liu , Sen Jia , Kankan Zhao , Ziwen Ke , Wenqi Huang , Haifeng Wang , Yanjie Zhu , Dong Liang

The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the training of deep networks for classification. We will show that…

Machine Learning · Computer Science 2020-04-14 Andrzej Banburski , Qianli Liao , Brando Miranda , Lorenzo Rosasco , Fernanda De La Torre , Jack Hidary , Tomaso Poggio

Gradient normalization stabilizes deep-learning optimization, and spectral normalizations are especially natural for matrix-shaped parameter blocks; Muon is the motivating example. We study an idealized deterministic, continuous-time,…

Optimization and Control · Mathematics 2026-05-11 Gabriel Peyré

In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO)…

Machine Learning · Computer Science 2020-02-10 Yangjun Ruan , Yuanhao Xiong , Sashank Reddi , Sanjiv Kumar , Cho-Jui Hsieh

Stochastic Bilevel optimization usually involves minimizing an upper-level (UL) function that is dependent on the arg-min of a strongly-convex lower-level (LL) function. Several algorithms utilize Neumann series to approximate certain…

Optimization and Control · Mathematics 2023-06-22 Xuxing Chen , Tesi Xiao , Krishnakumar Balasubramanian

Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other…

Machine Learning · Computer Science 2020-01-08 E Zhenqian , Gao Weiguo

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method…

Machine Learning · Computer Science 2024-05-24 Yuyan Zhou , Ye Li , Lei Feng , Sheng-Jun Huang

With the rapid growth in model size, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually focus on reducing the number of trainable parameters in the…

Traditional deep learning compilers rely on heuristics for subgraph generation, which impose extra constraints on graph optimization, e.g., each subgraph can only contain at most one complex operator. In this paper, we propose AGO, a…

Machine Learning · Computer Science 2022-12-05 Zhiying Xu , Hongding Peng , Wei Wang

Time-dependent partial differential equations are ubiquitous in physics-based modeling, but they remain computationally intensive in many-query scenarios, such as real-time forecasting, optimal control, and uncertainty quantification.…

Machine Learning · Computer Science 2026-01-26 Sven Dummer , Dongwei Ye , Christoph Brune