Scan and Snap: Understanding Training Dynamics and Token Composition in
1-layer Transformer

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer

25 May 2023

Papers citing "Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer"

15 / 15 papers shown

Title
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias Ruiquan Huang Yingbin Liang Jing Yang 43 0 0 02 May 2025
On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery Renpu Liu Ruida Zhou Cong Shen Jing Yang 23 0 0 17 Oct 2024
From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency Kaiyue Wen Huaqing Zhang Hongzhou Lin Jingzhao Zhang MoE LRM 54 2 0 07 Oct 2024
Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization Xinhao Yao Hongjin Qian Xiaolin Hu Gengze Xu Wei Liu Jian Luan B. Wang Y. Liu 41 0 0 03 Oct 2024
Attention layers provably solve single-location regression P. Marion Raphael Berthier Gérard Biau Claire Boyer 42 2 0 02 Oct 2024
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers Lorenzo Tiberi Francesca Mignacco Kazuki Irie H. Sompolinsky 36 5 0 24 May 2024
Linear Transformers are Versatile In-Context Learners Max Vladymyrov J. Oswald Mark Sandler Rong Ge 18 13 0 21 Feb 2024
Implicit Bias and Fast Convergence Rates for Self-attention Bhavya Vasudeva Puneesh Deora Christos Thrampoulidis 24 13 0 08 Feb 2024
An Information-Theoretic Analysis of In-Context Learning Hong Jun Jeon Jason D. Lee Qi Lei Benjamin Van Roy 13 18 0 28 Jan 2024
Do Transformers Parse while Predicting the Masked Word? Haoyu Zhao A. Panigrahi Rong Ge Sanjeev Arora 74 29 0 14 Mar 2023
How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding Yuchen Li Yuan-Fang Li Andrej Risteski 98 61 0 07 Mar 2023
In-context Learning and Induction Heads Catherine Olsson Nelson Elhage Neel Nanda Nicholas Joseph Nova Dassarma ... Tom B. Brown Jack Clark Jared Kaplan Sam McCandlish C. Olah 240 453 0 24 Sep 2022
Understanding Deep Contrastive Learning via Coordinate-wise Optimization Yuandong Tian 43 34 0 29 Jan 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 258 7,337 0 11 Nov 2021
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation Ofir Press Noah A. Smith M. Lewis 234 690 0 27 Aug 2021