English
Related papers

Related papers: Fourier Transformer: Fast Long Range Modeling by R…

200 papers

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the…

Machine Learning · Computer Science 2021-10-29 Hongyu Ren , Hanjun Dai , Zihang Dai , Mengjiao Yang , Jure Leskovec , Dale Schuurmans , Bo Dai

The complex world around us is inherently multimodal and sequential (continuous). Information is scattered across different modalities and requires multiple continuous sensors to be captured. As machine learning leaps towards better…

Machine Learning · Computer Science 2019-11-25 Amir Zadeh , Chengfeng Mao , Kelly Shi , Yiwei Zhang , Paul Pu Liang , Soujanya Poria , Louis-Philippe Morency

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 either inefficient on…

Computation and Language · Computer Science 2021-09-07 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…

Computation and Language · Computer Science 2025-05-05 Md Kowsher , Nusrat Jahan Prottasha , Chun-Nam Yu , Ozlem Ozmen Garibay , Niloofar Yousefi

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Trevor Dohm , Eric C. Larson

While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform,…

Machine Learning · Computer Science 2021-08-10 Muqiao Yang , Martin Q. Ma , Dongyu Li , Yao-Hung Hubert Tsai , Ruslan Salakhutdinov

Convolutional neural network (CNN) is one of the most widely-used successful architectures in the era of deep learning. However, the high-computational cost of CNN still hampers more universal uses to light devices. Fortunately, the Fourier…

Networking and Internet Architecture · Computer Science 2021-08-13 Xiaohan Zhu , Zhen Cui , Tong Zhang , Yong Li , Jian Yang

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

Computation and Language · Computer Science 2023-08-30 Hao Liu , Pieter Abbeel

Discrete cosine transform (DCT) and other Fourier-related transforms have broad applications in scientific computing. However, off-the-shelf high-performance multi-dimensional DCT (MD DCT) libraries are not readily available in parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-05 Zixuan Jiang , Jiaqi Gu , David Z. Pan

Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Cong Wang , Jinshan Pan , Yeying Jin , Liyan Wang , Wei Wang , Gang Fu , Wenqi Ren , Xiaochun Cao

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the weight change, i.e.,…

Machine Learning · Computer Science 2024-05-07 Ziqi Gao , Qichao Wang , Aochuan Chen , Zijing Liu , Bingzhe Wu , Liang Chen , Jia Li

This paper presents \textbf{FreEformer}, a simple yet effective model that leverages a \textbf{Fre}quency \textbf{E}nhanced Trans\textbf{former} for multivariate time series forecasting. Our work is based on the assumption that the…

Machine Learning · Computer Science 2025-01-27 Wenzhen Yue , Yong Liu , Xianghua Ying , Bowei Xing , Ruohao Guo , Ji Shi

The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this…

Sound · Computer Science 2025-06-27 Maxime Leiber , Yosra Marnissi , Axel Barrau , Sylvain Meignen , Laurent Massoulié

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yining Li , Dongchen Han , Zeyu Liu , Hanyi Wang , Yulin Wang , Gao Huang

We develop the basic building blocks of a frequency domain framework for drawing statistical inferences on the second-order structure of a stationary sequence of functional data. The key element in such a context is the spectral density…

Statistics Theory · Mathematics 2013-05-10 Victor M. Panaretos , Shahin Tavakoli

The nonlinear Fourier transform (NFT) has recently gained significant attention in fiber optic communications and other engineering fields. Although several numerical algorithms for computing the NFT have been published, the design of…

Signal Processing · Electrical Eng. & Systems 2019-10-17 Shrinivas Chimmalgi , Peter J. Prins , Sander Wahls

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Zhihang Yuan , Hanling Zhang , Pu Lu , Xuefei Ning , Linfeng Zhang , Tianchen Zhao , Shengen Yan , Guohao Dai , Yu Wang