English
Related papers

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

200 papers

We study learning to learn for the multi-task structured bandit problem where the goal is to learn a near-optimal algorithm that minimizes cumulative regret. The tasks share a common structure and an algorithm should exploit the shared…

Machine Learning · Computer Science 2025-10-24 Subhojyoti Mukherjee , Josiah P. Hanna , Qiaomin Xie , Robert Nowak

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM),…

Machine Learning · Computer Science 2025-10-21 Jing Liu

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Machine Learning · Computer Science 2024-09-27 Tong Yang , Yu Huang , Yingbin Liang , Yuejie Chi

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

In this article a surprising result is demonstrated using the neural tangent kernel. This kernel is defined as the inner product of the vector of the gradient of an underlying model evaluated at training points. This kernel is used to…

Artificial Intelligence · Computer Science 2021-04-14 Matt Calder

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

We explore the capability of transformers to address endogeneity in in-context linear regression. Our main finding is that transformers inherently possess a mechanism to handle endogeneity effectively using instrumental variables (IV).…

Machine Learning · Statistics 2025-05-13 Haodong Liang , Krishnakumar Balasubramanian , Lifeng Lai

Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable approach shifting the expensive combinatorial search to a…

Machine Learning · Computer Science 2025-09-25 Henrik Voigt , Paul Kahlmeyer , Kai Lawonn , Michael Habeck , Joachim Giesen

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

This paper investigates approximation-theoretic aspects of the in-context learning capability of the transformers in representing a family of noisy linear dynamical systems. Our first theoretical result establishes an upper bound on the…

Machine Learning · Computer Science 2025-10-22 Frank Cole , Yuxuan Zhao , Yulong Lu , Tianhao Zhang

Regression models for supervised learning problems with a continuous target are commonly understood as models for the conditional mean of the target given predictors. This notion is simple and therefore appealing for interpretation and…

Methodology · Statistics 2018-01-09 Torsten Hothorn , Achim Zeileis

While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic…

Machine Learning · Computer Science 2023-10-17 Tianyu Guo , Wei Hu , Song Mei , Huan Wang , Caiming Xiong , Silvio Savarese , Yu Bai

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…

Machine Learning · Computer Science 2023-11-15 Vedant Nanda , Till Speicher , John P. Dickerson , Soheil Feizi , Krishna P. Gummadi , Adrian Weller

Non-stationary sequences arise naturally in control, forecasting, and decision-making. The data-generating process shifts at unknown times, and models must detect the change, discard or downweight obsolete evidence, and adapt to new…

Machine Learning · Computer Science 2026-04-21 Carson Dudley , Yutong Bi , Xiaofeng Liu , Samet Oymak

What computational structure are we building into large language models when we train them on next-token prediction? Here, we present evidence that this structure is given by the meta-dynamics of belief updating over hidden states of the…

Machine Learning · Computer Science 2025-02-05 Adam S. Shai , Sarah E. Marzen , Lucas Teixeira , Alexander Gietelink Oldenziel , Paul M. Riechers

Deep Learning models enjoy considerable success in Natural Language Processing. While deep architectures produce useful representations that lead to improvements in various tasks, they are often difficult to interpret. This makes the…

Computation and Language · Computer Science 2013-04-29 Christian Scheible , Hinrich Schuetze

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

Transformers exhibit in-context learning (ICL): the ability to use novel information presented in the context without additional weight updates. Recent work shows that ICL emerges when models are trained on a sufficiently diverse set of…

Machine Learning · Computer Science 2024-12-13 Alex Nguyen , Gautam Reddy

We here present a stepping stone towards a deeper understanding of convolutional neural networks (CNNs) in the form of a theory of learning in linear CNNs. Through analyzing the gradient descent equations, we discover that the evolution of…

Computer Vision and Pattern Recognition · Computer Science 2023-07-26 Hannah Pinson , Joeri Lenaerts , Vincent Ginis

Understanding how neural networks learn remains one of the central challenges in machine learning research. From random at the start of training, the weights of a neural network evolve in such a way as to be able to perform a variety of…

Machine Learning · Computer Science 2020-10-28 Maxime Gabella