English
Related papers

Related papers: Transformers learn through gradual rank increase

200 papers

Modern deep neural networks display striking examples of rich internal computational structure. Uncovering principles governing the development of such structure is a priority for the science of deep learning. In this paper, we explore the…

Machine Learning · Computer Science 2025-02-03 Liam Carroll , Jesse Hoogland , Matthew Farrugia-Roberts , Daniel Murfet

Time series forecasting with limited data is a challenging yet critical task. While transformers have achieved outstanding performances in time series forecasting, they often require many training samples due to the large number of…

Machine Learning · Computer Science 2019-10-23 Yunkai Zhang , Qiao Jiang , Shurui Li , Xiaoyong Jin , Xueying Ma , Xifeng Yan

In-context learning, i.e., learning from context examples, is an impressive ability of Transformer. Training Transformers to possess this in-context learning skill is computationally intensive due to the occurrence of learning plateaus,…

Machine Learning · Computer Science 2024-06-07 Jingwen Fu , Tao Yang , Yuwang Wang , Yan Lu , Nanning Zheng

We study the dynamics of supervised learning in layered neural networks, in the regime where the size $p$ of the training set is proportional to the number $N$ of inputs. Here the local fields are no longer described by Gaussian probability…

Disordered Systems and Neural Networks · Physics 2009-10-31 A. C. C. Coolen , D. Saad

Transformers have become the dominant architecture for natural language processing. Part of their success is owed to a remarkable capability known as in-context learning (ICL): they can acquire and apply novel associations solely from their…

Artificial Intelligence · Computer Science 2026-01-12 Tiberiu Musat , Tiago Pimentel , Lorenzo Noci , Alessandro Stolfo , Mrinmaya Sachan , Thomas Hofmann

For a sequence of classification tasks that arrive over time, it is common that tasks are evolving in the sense that consecutive tasks often have a higher similarity. The incremental learning of a growing sequence of tasks holds promise to…

Machine Learning · Statistics 2023-10-25 Verónica Álvarez , Santiago Mazuelas , Jose A. Lozano

Recent empirical evidence has demonstrated that the training dynamics of large-scale deep neural networks occur within low-dimensional subspaces. While this has inspired new research into low-rank training, compression, and adaptation,…

Machine Learning · Computer Science 2026-02-09 Alec S. Xu , Can Yaras , Matthew Asato , Qing Qu , Laura Balzano

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

Machine Learning · Computer Science 2024-11-19 Deqing Fu , Tian-Qi Chen , Robin Jia , Vatsal Sharan

Transformers may exhibit two-stage training dynamics during the real-world training process. For instance, when training GPT-2 on the Counterfact dataset, the answers progress from syntactically incorrect to syntactically correct to…

Computation and Language · Computer Science 2025-10-14 Zixuan Gong , Shijia Li , Yong Liu , Jiaye Teng

Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Romain Couillet

We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality. In a second step,…

Computer Vision and Pattern Recognition · Computer Science 2017-07-11 Marco Loog , François Lauze

Designing learning systems which are invariant to certain data transformations is critical in machine learning. Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e.g.…

Machine Learning · Computer Science 2022-10-26 Cédric Rommel , Thomas Moreau , Alexandre Gramfort

In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly…

Machine Learning · Computer Science 2025-07-29 Anil Radhakrishnan , John F. Lindner , Scott T. Miller , Sudeshna Sinha , William L. Ditto

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers…

Machine Learning · Computer Science 2023-12-01 Zhiqiu Xu , Yanjie Chen , Kirill Vishniakov , Yida Yin , Zhiqiang Shen , Trevor Darrell , Lingjie Liu , Zhuang Liu

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in…

Artificial Intelligence · Computer Science 2017-03-09 Abhishek Gupta , Coline Devin , YuXuan Liu , Pieter Abbeel , Sergey Levine

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

Understanding the training dynamics of transformers is important to explain the impressive capabilities behind large language models. In this work, we study the dynamics of training a shallow transformer on a task of recognizing…

Machine Learning · Computer Science 2024-10-15 Hongru Yang , Bhavya Kailkhura , Zhangyang Wang , Yingbin Liang

Continual Learning is a learning paradigm where learning systems are trained with sequential or streaming tasks. Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based…

Machine Learning · Computer Science 2020-02-24 Abhishek Kumar , Sunabha Chatterjee , Piyush Rai

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…

Machine Learning · Computer Science 2023-03-29 Tongzhou Mu , Hao Su

Building invariance to non-meaningful transformations is essential to building efficient and generalizable machine learning models. In practice, the most common way to learn invariance is through data augmentation. There has been recent…

Machine Learning · Computer Science 2021-06-09 Scott Mahan , Henry Kvinge , Tim Doster