English
Related papers

Related papers: Training Dynamics of Multi-Head Softmax Attention …

200 papers

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical…

Machine Learning · Computer Science 2025-10-09 Zheng-An Chen , Tao Luo

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

In recent years, transformer architectures have revolutionized the field of language processing, opening the door to previously unforeseen possibilities. However, from a theoretical point of view, the mathematical models proposed in the…

Machine Learning · Computer Science 2026-05-20 Alex Massucco , Leonardo Del Grande , Marcello Carioni , Christoph Brune , Carola-Bibiane Schönlieb

Fitting neural networks often resorts to stochastic (or similar) gradient descent which is a noise-tolerant (and efficient) resolution of a gradient descent dynamics. It outputs a sequence of networks parameters, which sequence evolves…

Machine Learning · Statistics 2021-04-15 Gabriel Turinici

Equipping a deep model the abaility of few-shot learning, i.e., learning quickly from only few examples, is a core challenge for artificial intelligence. Gradient-based meta-learning approaches effectively address the challenge by learning…

Machine Learning · Computer Science 2024-01-09 Baoquan Zhang , Chuyao Luo , Demin Yu , Huiwei Lin , Xutao Li , Yunming Ye , Bowen Zhang

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Machine Learning · Computer Science 2026-02-27 O. Duranthon , P. Marion , C. Boyer , B. Loureiro , L. Zdeborová

Transformer models exhibit remarkable in-context learning (ICL), adapting to novel tasks from examples within their context, yet the underlying mechanisms remain largely mysterious. Here, we provide an exact analytical characterization of…

Machine Learning · Computer Science 2025-11-25 Nischal Mainali , Lucas Teixeira

Transformers have achieved remarkable successes across a wide range of applications, yet the theoretical foundation of their model efficiency remains underexplored. In this work, we investigate how the model parameters -- mainly attention…

Machine Learning · Computer Science 2025-10-07 Ruoxi Yu , Haotian Jiang , Jingpu Cheng , Penghao Yu , Qianxiao Li , Zhong Li

Prompt-tuning is an emerging strategy to adapt large language models (LLM) to downstream tasks by learning a (soft-)prompt parameter from data. Despite its success in LLMs, there is limited theoretical understanding of the power of…

Machine Learning · Computer Science 2023-06-07 Samet Oymak , Ankit Singh Rawat , Mahdi Soltanolkotabi , Christos Thrampoulidis

The unusual properties of in-context learning (ICL) have prompted investigations into the internal mechanisms of large language models. Prior work typically focuses on either special attention heads or task vectors at specific layers, but…

Computation and Language · Computer Science 2025-10-21 Haolin Yang , Hakaze Cho , Yiqiao Zhong , Naoya Inoue

We study continual learning on multiple linear classification tasks by sequentially running gradient descent (GD) for a fixed budget of iterations per task. When all tasks are jointly linearly separable and are presented in a cyclic/random…

Machine Learning · Computer Science 2025-04-29 Hyunji Jung , Hanseul Cho , Chulhee Yun

The recipe behind the success of deep learning has been the combination of neural networks and gradient-based optimization. Understanding the behavior of gradient descent however, and particularly its instability, has lagged behind its…

Machine Learning · Statistics 2023-09-15 Mihaela Rosca , Yan Wu , Chongli Qin , Benoit Dherin

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Accurate perception of dynamic traffic scenes is crucial for high-level autonomous driving systems, requiring robust object motion estimation and instance segmentation. However, traditional methods often treat them as separate tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Yinqi Chen , Meiying Zhang , Qi Hao , Guang Zhou

The field of artificial neural network (ANN) training has garnered significant attention in recent years, with researchers exploring various mathematical techniques for optimizing the training process. In particular, this paper focuses on…

Functional Analysis · Mathematics 2023-06-23 Arzu Ahmadova

Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module:…

Computation and Language · Computer Science 2023-10-17 Chong Li , Shaonan Wang , Yunhao Zhang , Jiajun Zhang , Chengqing Zong

Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…

Human-Computer Interaction · Computer Science 2020-09-16 Joseph F DeRose , Jiayao Wang , Matthew Berger

In-context learning based on attention models is examined for data with categorical outcomes, with inference in such models viewed from the perspective of functional gradient descent (GD). We develop a network composed of attention blocks,…

Machine Learning · Statistics 2025-05-08 Aaron T. Wang , William Convertino , Xiang Cheng , Ricardo Henao , Lawrence Carin

Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the model behaves as though it had summarised the context into a population-level statistic…

Machine Learning · Computer Science 2026-05-12 Haoren Xu , Guanhua Fang

While much progress has been achieved over the last decades in neuro-inspired machine learning, there are still fundamental theoretical problems in gradient-based learning using combinations of neurons. These problems, such as saddle points…

Machine Learning · Computer Science 2023-06-16 Winfried Lohmiller , Philipp Gassert , Jean-Jacques Slotine