English
Related papers

Related papers: Learning Rate Transfer in Normalized Transformers

200 papers

In this work, we study the transfer learning problem under high-dimensional generalized linear models (GLMs), which aim to improve the fit on target data by borrowing information from useful source data. Given which sources to transfer, we…

Machine Learning · Statistics 2022-04-19 Ye Tian , Yang Feng

Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The maximal update parameterization ({\mu}P) ensures transfer through principled mathematical…

Training large language models at 4-bit precision is critical for efficiency. We show that nGPT, an architecture that constrains weights and hidden representations to the unit hypersphere, is inherently more robust to low-precision…

Machine Learning · Computer Science 2026-05-08 Maxim Fishman , Brian Chmiel , Ron Banner , Daniel Soudry , Boris Ginsburg

Inferring properties of graph-structured data, e.g., the solubility of molecules, essentially involves learning the implicit mapping from graphs to their properties. This learning process is often costly for graph property learners like…

Machine Learning · Computer Science 2025-05-22 Chen Zhang , Weixin Bu , Zeyi Ren , Zhengwu Liu , Yik-Chung Wu , Ngai Wong

We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. Given a graph, we simply treat all nodes and edges as independent tokens, augment them with…

Machine Learning · Computer Science 2022-10-25 Jinwoo Kim , Tien Dat Nguyen , Seonwoo Min , Sungjun Cho , Moontae Lee , Honglak Lee , Seunghoon Hong

We introduce the Graded Transformer framework, a new class of sequence models that embeds algebraic inductive biases through grading transformations on vector spaces. Extending Graded Neural Networks (GNNs), we propose two architectures:…

Machine Learning · Computer Science 2025-09-03 Tony Shaska

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…

Computation and Language · Computer Science 2018-05-03 Martin Popel , Ondřej Bojar

Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data, especially in next-token prediction (NTP) tasks. However, the theoretical understanding of their…

Machine Learning · Computer Science 2024-10-01 Ruiquan Huang , Yingbin Liang , Jing Yang

Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network…

Machine Learning · Computer Science 2026-05-29 Javier Porras-Valenzuela , Zhiyang Wang , Xiaotao Shang , Yusu Wang , Alejandro Ribeiro

Transformers have recently emerged as powerful neural networks for graph learning, showcasing state-of-the-art performance on several graph property prediction tasks. However, these results have been limited to small-scale graphs, where the…

Machine Learning · Computer Science 2023-12-19 Vijay Prakash Dwivedi , Yozen Liu , Anh Tuan Luu , Xavier Bresson , Neil Shah , Tong Zhao

Graph neural networks (GNNs) use graph convolutions to exploit network invariances and learn meaningful feature representations from network data. However, on large-scale graphs convolutions incur in high computational cost, leading to…

Machine Learning · Computer Science 2022-06-29 Juan Cervino , Luana Ruiz , Alejandro Ribeiro

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained…

Machine Learning · Computer Science 2023-10-04 Daiki Chijiwa

Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the knowledge learned in the…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Yi Zhu , Jia Xue , Shawn Newsam

We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message…

Machine Learning · Computer Science 2025-06-30 Chaitanya K. Joshi

Length generalization, defined as the ability to extrapolate from shorter training sequences to longer test ones, is a significant challenge for language models. This issue persists even with large-scale Transformers handling relatively…

Machine Learning · Computer Science 2024-02-15 Yongchao Zhou , Uri Alon , Xinyun Chen , Xuezhi Wang , Rishabh Agarwal , Denny Zhou

We study the optimization of wide neural networks (NNs) via gradient flow (GF) in setups that allow feature learning while admitting non-asymptotic global convergence guarantees. First, for wide shallow NNs under the mean-field scaling and…

Machine Learning · Computer Science 2022-04-25 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

We develop new transfer learning algorithms to accelerate prediction of material properties from ab initio simulations based on density functional theory (DFT). Transfer learning has been successfully utilized for data-efficient modeling in…

Computational Physics · Physics 2020-07-01 Schuyler Krawczuk , Daniele Venturi

We study the transfer learning process between two linear regression problems. An important and timely special case is when the regressors are overparameterized and perfectly interpolate their training data. We examine a parameter transfer…

Machine Learning · Computer Science 2022-09-29 Yehuda Dar , Richard G. Baraniuk

Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs…

Machine learning requires exuberant amounts of data and computation. Also, models require equally excessive growth in the number of parameters. It is, therefore, sensible to look for technologies that reduce these demands on resources.…

Machine Learning · Computer Science 2023-03-29 Danko Nikolić , Davor Andrić , Vjekoslav Nikolić