English
Related papers

Related papers: Dynamics of Transient Structure in In-Context Line…

200 papers

Deep neural networks give us a powerful method to model the training dataset's relationship between input and output. We can regard that as a complex adaptive system consisting of many artificial neurons that work as an adaptive memory as a…

Disordered Systems and Neural Networks · Physics 2024-05-08 Kenichi Nakazato

This work presents a novel means for understanding learning dynamics and scaling relations in neural networks. We show that certain measures on the spectrum of the empirical neural tangent kernel, specifically entropy and trace, yield…

Machine Learning · Computer Science 2024-10-11 Samuel Tovey , Sven Krippendorf , Michael Spannowsky , Konstantin Nikolaou , Christian Holm

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Wide neural networks with linear output layer have been shown to be near-linear, and to have near-constant neural tangent kernel (NTK), in a region containing the optimization path of gradient descent. These findings seem counter-intuitive…

Machine Learning · Computer Science 2022-03-11 Chaoyue Liu , Libin Zhu , Mikhail Belkin

Advancements in artificial intelligence call for a deeper understanding of the fundamental mechanisms underlying deep learning. In this work, we propose a theoretical framework to analyze learning dynamics through the lens of dynamical…

Machine Learning · Computer Science 2025-10-13 Yuchen Lin , Yong Zhang , Sihan Feng , Hong Zhao

Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trained to solve. In this paper, we study the in-context…

Machine Learning · Computer Science 2023-06-27 Jonathan N. Lee , Annie Xie , Aldo Pacchiano , Yash Chandak , Chelsea Finn , Ofir Nachum , Emma Brunskill

Regression models usually tend to recover a noisy signal in the form of a combination of regressors, also called features in machine learning, themselves being the result of a learning process.The alignment of the prior covariance feature…

Statistical Mechanics · Physics 2023-01-25 Cyril Furtlehner

From benign overfitting in overparameterized models to rich power-law scalings in performance, simple ridge regression displays surprising behaviors sometimes thought to be limited to deep neural networks. This balance of phenomenological…

Machine Learning · Statistics 2026-05-08 Alexander Atanasov , Jacob A. Zavatone-Veth , Cengiz Pehlevan

Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks. However, the solutions found by learning and the effect of initial connectivity are not well understood. Here,…

Neurons and Cognition · Quantitative Biology 2021-05-17 Friedrich Schuessler , Francesca Mastrogiuseppe , Alexis Dubreuil , Srdjan Ostojic , Omri Barak

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

We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on a source task improves generalization on a target task. We analyze both (i) fine-tuning, when the downstream…

Machine Learning · Computer Science 2026-02-25 Clarissa Lauditi , Blake Bordelon , Cengiz Pehlevan

Many neural network architectures are known to be Turing Complete, and can thus, in principle implement arbitrary algorithms. However, Transformers are unique in that they can implement gradient-based learning algorithms under simple…

Machine Learning · Computer Science 2024-06-05 Xiang Cheng , Yuxin Chen , Suvrit Sra

Deep convolutional neural networks have achieved impressive performance on a broad range of problems, beating prior art on established benchmarks, but it often remains unclear what are the representations learnt by those systems and how…

Computer Vision and Pattern Recognition · Computer Science 2018-03-23 Sen He , Nicolas Pugeault

Over-parameterized models like deep nets and random forests have become very popular in machine learning. However, the natural goals of continuity and differentiability, common in regression models, are now often ignored in modern…

Machine Learning · Computer Science 2023-10-16 Mingxuan Han , Varun Shankar , Jeff M Phillips , Chenglong Ye

In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate empirically the conditions necessary on the pretraining…

Machine Learning · Computer Science 2025-12-11 Chase Goddard , Lindsay M. Smith , Vudtiwat Ngampruetikorn , David J. Schwab

We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks…

Machine Learning · Computer Science 2025-05-27 Frank Cole , Yulong Lu , Wuzhe Xu , Tianhao Zhang

Increase in data, size, or compute can lead to sudden learning of specific capabilities by a neural network -- a phenomenon often called "emergence''. Beyond scientific understanding, establishing the causal factors underlying such emergent…

Machine Learning · Computer Science 2024-09-10 Ekdeep Singh Lubana , Kyogo Kawaguchi , Robert P. Dick , Hidenori Tanaka

Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted with training and test examples, without any parameter…

Machine Learning · Computer Science 2023-07-07 Yu Bai , Fan Chen , Huan Wang , Caiming Xiong , Song Mei

Large transformers are powerful architectures used for self-supervised data analysis across various data types, including protein sequences, images, and text. In these models, the semantic structure of the dataset emerges from a sequence of…

Machine Learning · Computer Science 2023-10-31 Lucrezia Valeriani , Diego Doimo , Francesca Cuturello , Alessandro Laio , Alessio Ansuini , Alberto Cazzaniga

Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Stanisław Jastrzębski , Devansh Arpit , Nicolas Ballas , Vikas Verma , Tong Che , Yoshua Bengio