paper-with-me

Papers

Linear attention is (maybe) all you need (to understand transformer optimization)

2023-10-02 · Kwangjun Ahn, Xiang Cheng, Minhak Song, Chulhee Yun, Ali Jadbabaie, Suvrit Sra

Transformer training is notoriously difficult, requiring a careful design of optimizers and use of various heuristics. We make progress towards understanding the subtleties of training Transformers by carefully studying a simple yet canonical linearized shallow Transformer model. Specifically, we train linear Transformers to solve regression tasks, inspired by J.~von Oswald et al.~(ICML 2023), and K.~Ahn et al.~(NeurIPS 2023). Most importantly, we observe that our proposed linearized models can reproduce several prominent aspects of Transformer training dynamics. Consequently, the results obtained in this paper suggest that a simple linearized Transformer model could actually be a valuable, realistic abstraction for understanding Transformer optimization.

📄 PDF Abstract BibTeX arXiv:2310.01082

Code (1)

chengxiang/lineartransformer pytorch

Tasks

All

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention

2022-03-08 · Kai Liu, Tianyi Wu, Cong Liu, Guodong Guo

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by each query attending to all keys/values, various methods have constrained the rang…

image-classificationImage ClassificationInstance Segmentationobject-detection+2

B-Cos Aligned Transformers Learn Human-Interpretable Features

2024-01-16 · Manuel Tran, Amal Lahiani, Yashin Dicente Cid, Melanie Boxberg 외

Vision Transformers (ViTs) and Swin Transformers (Swin) are currently state-of-the-art in computational pathology. However, domain experts are still reluctant to use these models due to their lack of interpretability. Th…

Pay Attention to Virality: understanding popularity of social media videos with the attention mechanism

2018-04-26 · Adam Bielski, Tomasz Trzcinski

Predicting popularity of social media videos before they are published is a challenging task, mainly due to the complexity of content distribution network as well as the number of factors that play part in this process. …

Fastformer: Additive Attention Can Be All You Need

2021-08-20 · Chuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang 외

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still eit…

AllNews RecommendationText ClassificationText Summarization

Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization

2022-08-01 · Tan Nguyen, Richard G. Baraniuk, Robert M. Kirby, Stanley J. Osher 외

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques includ…

Image GenerationMachine Translation