English
Related papers

Related papers: Learning Rate Transfer in Normalized Transformers

200 papers

Graph Neural Networks (GNNs) have achieved remarkable success across diverse tasks on graph-structured data, primarily through the use of learned weights in message passing layers. In this paper, we demonstrate that random weights can be…

Machine Learning · Computer Science 2025-02-04 Thu Bui , Carola-Bibiane Schönlieb , Bruno Ribeiro , Beatrice Bevilacqua , Moshe Eliasof

Parameter transfer is a central paradigm in transfer learning, enabling knowledge reuse across tasks and domains by sharing model parameters between upstream and downstream models. However, when only a subset of parameters from the upstream…

Machine Learning · Computer Science 2026-01-08 Hua Yuan , Xuran Meng , Qiufeng Wang , Shiyu Xia , Ning Xu , Xu Yang , Jing Wang , Xin Geng , Yong Rui

We generalise Spatial Transformer Networks (STN) by replacing the parametric transformation of a fixed, regular sampling grid with a deformable, statistical shape model which is itself learnt. We call this a Statistical Transformer Network…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Anil Bas , William A. P. Smith

The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\mu$P parameterized networks, where the…

Machine Learning · Statistics 2023-12-11 Blake Bordelon , Lorenzo Noci , Mufan Bill Li , Boris Hanin , Cengiz Pehlevan

Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have attempted to migrate Transformers to graph learning, but most…

Machine Learning · Computer Science 2026-01-30 Liheng Ma , Soumyasundar Pal , Yingxue Zhang , Philip H. S. Torr , Mark Coates

Graph Neural Networks (GNNs) have attracted considerable attention and have emerged as a new promising paradigm to process graph-structured data. GNNs are usually stacked to multiple layers and the node representations in each layer are…

Machine Learning · Computer Science 2020-09-25 Yihao Chen , Xin Tang , Xianbiao Qi , Chun-Guang Li , Rong Xiao

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matrix dimensions. Generation is further complicated by permutation symmetries that allow…

Machine Learning · Computer Science 2026-03-03 Jiwoo Kim , Swarajh Mehta , Hao-Lun Hsu , Hyunwoo Ryu , Yudong Liu , Miroslav Pajic

The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that…

Machine Learning · Computer Science 2020-06-02 Zeyuan Allen-Zhu , Yuanzhi Li , Yingyu Liang

Graph pre-training has been concentrated on graph-level tasks involving small graphs (e.g., molecular graphs) or learning node representations on a fixed graph. Extending graph pre-trained models to web-scale graphs with billions of nodes…

Machine Learning · Computer Science 2025-11-07 Yufei He , Zhenyu Hou , Yukuo Cen , Jun Hu , Feng He , Xu Cheng , Jie Tang , Bryan Hooi

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

Machine Learning · Computer Science 2025-11-11 Zeman Li , Ali Behrouz , Yuan Deng , Peilin Zhong , Praneeth Kacham , Mahdi Karami , Meisam Razaviyayn , Vahab Mirrokni

Graph neural networks (GNNs) are composed of layers consisting of graph convolutions and pointwise nonlinearities. Due to their invariance and stability properties, GNNs are provably successful at learning representations from data…

Machine Learning · Computer Science 2023-08-09 Luana Ruiz , Luiz F. O. Chamon , Alejandro Ribeiro

We study compute efficiency of LLM training when using different parameterizations, i.e., rules for adjusting model and optimizer hyperparameters (HPs) as model size changes. Some parameterizations fail to transfer optimal base HPs (such as…

Machine Learning · Computer Science 2026-01-21 Nolan Dey , Bin Claire Zhang , Lorenzo Noci , Mufan Li , Blake Bordelon , Shane Bergsma , Cengiz Pehlevan , Boris Hanin , Joel Hestness

Embedding tables are usually huge in click-through rate (CTR) prediction models. To train and deploy the CTR models efficiently and economically, it is necessary to compress their embedding tables at the training stage. To this end, we…

Machine Learning · Computer Science 2024-08-07 Shiwei Li , Huifeng Guo , Lu Hou , Wei Zhang , Xing Tang , Ruiming Tang , Rui Zhang , Ruixuan Li

Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model upscaling: initializing larger models from trained smaller…

Machine Learning · Computer Science 2026-02-12 Yuxin Ma , Nan Chen , Mateo Díaz , Soufiane Hayou , Dmitriy Kunisky , Soledad Villar

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

The growing complexity of wireless systems has accelerated the move from traditional methods to learning-based solutions. Graph Neural Networks (GNNs) are especially well-suited here, since wireless networks can be naturally represented as…

Signal Processing · Electrical Eng. & Systems 2025-10-02 Romina Garcia Camargo , Zhiyang Wang , Alejandro Ribeiro

The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametric forms of nonlinear activation functions. The nonlinear forms proposed for performing the…

Information Retrieval · Computer Science 2021-02-08 Abdourrahmane Mahamane Atto , Sylvie Galichet , Dominique Pastor , Nicolas Méger

We present Generalizable NeRF Transformer (GNT), a transformer-based architecture that reconstructs Neural Radiance Fields (NeRFs) and learns to renders novel views on the fly from source views. While prior works on NeRFs optimize a scene…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Mukund Varma T , Peihao Wang , Xuxi Chen , Tianlong Chen , Subhashini Venugopalan , Zhangyang Wang

Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the…

Machine Learning · Statistics 2023-10-13 Steve Hanneke , Samory Kpotufe , Yasaman Mahdaviyeh