English
Related papers

Related papers: Transformers Learn to Achieve Second-Order Converg…

200 papers

Transformer models exhibit in-context learning: the ability to accurately predict the response to a novel query based on illustrative examples in the input sequence. In-context learning contrasts with traditional in-weights learning of…

Machine Learning · Computer Science 2023-12-07 Gautam Reddy

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 analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

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

The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years. While theoretical understanding has been obtained for ICL in reinforcement learning (RL),…

Machine Learning · Statistics 2024-11-03 Chengshuai Shi , Kun Yang , Jing Yang , Cong Shen

In-context learning (ICL) enables transformers to adapt to new tasks through contextual examples without parameter updates. While existing research has typically studied ICL in fixed-complexity environments, practical language models…

Machine Learning · Computer Science 2025-06-25 Puneesh Deora , Bhavya Vasudeva , Tina Behnia , Christos Thrampoulidis

State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make…

Computation and Language · Computer Science 2020-02-18 Maha Elbayad , Jiatao Gu , Edouard Grave , Michael Auli

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hao Li , Hong Zhang , Xiaojuan Qi , Ruigang Yang , Gao Huang

What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer fine-tuned with…

Machine Learning · Computer Science 2025-01-27 Micah Rentschler , Jesse Roberts

Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also…

Machine Learning · Computer Science 2025-02-27 Jaehyeon Son , Soochan Lee , Gunhee Kim

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep methods, high-order methods, and multi-particle dynamical systems.…

Computation and Language · Computer Science 2024-11-06 Bei Li , Tong Zheng , Rui Wang , Jiahao Liu , Qingyan Guo , Junliang Guo , Xu Tan , Tong Xiao , Jingbo Zhu , Jingang Wang , Xunliang Cai

In-context learning (ICL) in large language models (LLMs) is a striking phenomenon, yet its underlying mechanisms remain only partially understood. Previous work connects linear self-attention (LSA) to gradient descent (GD), this connection…

Machine Learning · Computer Science 2025-12-05 Shifeng Xie , Rui Yuan , Simone Rossi , Thomas Hannagan

Normalized gradient descent has shown substantial success in speeding up the convergence of exponentially-tailed loss functions (which includes exponential and logistic losses) on linear classifiers with separable data. In this paper, we go…

Machine Learning · Computer Science 2023-06-28 Hossein Taheri , Christos Thrampoulidis

Deep learning has revolutionized the computer vision and image classification domains. In this context Convolutional Neural Networks (CNNs) based architectures are the most widely applied models. In this article, we introduced two…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Seyedsaman Emami , Gonzalo Martínez-Muñoz

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 K J Joseph , Jathushan Rajasegaran , Salman Khan , Fahad Shahbaz Khan , Vineeth N Balasubramanian

Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt…

Statistics Theory · Mathematics 2024-05-13 Karthik Duraisamy

Transformer models have established new benchmarks in natural language processing; however, their increasing depth results in substantial growth in parameter counts. While existing recurrent transformer methods address this issue by…

Computation and Language · Computer Science 2025-05-27 Anthony Nguyen , Wenjun Lin

Gravity inversion is the problem of estimating subsurface density distributions from observed gravitational field data. We consider the two-dimensional (2D) case, in which recovering density models from one-dimensional (1D) measurements…

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate…

Machine Learning · Computer Science 2025-06-27 Daniel Wurgaft , Ekdeep Singh Lubana , Core Francisco Park , Hidenori Tanaka , Gautam Reddy , Noah D. Goodman

This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The…

Neural and Evolutionary Computing · Computer Science 2021-03-02 Richard J. Preen , Larry Bull
‹ Prev 1 8 9 10 Next ›