English
Related papers

Related papers: On the Distribution, Sparsity, and Inference-time …

200 papers

Transformers demonstrate competitive performance in terms of precision on the problem of vision-based object detection. However, they require considerable computational resources due to the quadratic size of the attention weights. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Giorgos Savathrakis , Antonis Argyros

Quantization techniques can reduce the size of Deep Neural Networks and improve inference latency and throughput by taking advantage of high throughput integer instructions. In this paper we review the mathematical aspects of quantization…

Machine Learning · Computer Science 2020-04-22 Hao Wu , Patrick Judd , Xiaojie Zhang , Mikhail Isaev , Paulius Micikevicius

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Computation and Language · Computer Science 2023-03-15 Neşet Özkan Tan , Alex Yuxuan Peng , Joshua Bensemann , Qiming Bao , Tim Hartill , Mark Gahegan , Michael Witbrock

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning…

Machine Learning · Computer Science 2023-03-23 Elias Frantar , Dan Alistarh

Modern neural networks, although achieving state-of-the-art results on many tasks, tend to have a large number of parameters, which increases training time and resource usage. This problem can be alleviated by pruning. Existing methods,…

Machine Learning · Computer Science 2020-09-08 Andrei Apostol , Maarten Stol , Patrick Forré

The increasing size of large language models (LLMs) has introduced challenges in their training and inference. Removing model components is perceived as a solution to tackle the large model sizes, however, existing pruning methods solely…

Computation and Language · Computer Science 2023-12-27 Abdelrahman Zayed , Goncalo Mordido , Samira Shabanian , Ioana Baldini , Sarath Chandar

Transformers are becoming the mainstream solutions for various tasks like NLP and Computer vision. Despite their success, the high complexity of the attention mechanism hinders them from being applied to latency-sensitive tasks. Tremendous…

Machine Learning · Computer Science 2022-03-02 Zhaodong Chen , Yuying Quan , Zheng Qu , Liu Liu , Yufei Ding , Yuan Xie

Chain-of-thought (CoT) significantly enhances the reasoning performance of large language models (LLM). While current theoretical studies often attribute this improvement to increased expressiveness and computational capacity, we argue that…

Machine Learning · Computer Science 2025-03-06 Kaiyue Wen , Huaqing Zhang , Hongzhou Lin , Jingzhao Zhang

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

In this work we introduce a new transformer architecture called SparseDistilBERT (SDBERT), which is a combination of sparse attention and knowledge distillantion (KD). We implemented sparse attention mechanism to reduce quadratic dependency…

Computation and Language · Computer Science 2022-08-23 Devaraju Vinoda , Pawan Kumar Yadav

The multi-head self-attention of popular transformer models is widely used within Natural Language Processing (NLP), including for the task of extractive summarization. With the goal of analyzing and pruning the parameter-heavy…

Computation and Language · Computer Science 2020-12-04 Wen Xiao , Patrick Huber , Giuseppe Carenini

Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling…

Machine Learning · Computer Science 2022-06-17 Haixu Wu , Jialong Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex…

Machine Learning · Computer Science 2024-06-26 Hongkang Li , Meng Wang , Shuai Zhang , Sijia Liu , Pin-Yu Chen

In pursuit of faster computation, Efficient Transformers demonstrate an impressive variety of approaches -- models attaining sub-quadratic attention complexity can utilize a notion of sparsity or a low-rank approximation of inputs to reduce…

Machine Learning · Computer Science 2022-11-09 Uladzislau Yorsh , Alexander Kovalenko

Neural networks achieve state-of-the-art performance in image classification, speech recognition, scientific analysis and many more application areas. Due to the high computational complexity and memory footprint of neural networks, various…

Hardware Architecture · Computer Science 2025-04-21 Benjamin Ramhorst , Vladimir Loncar , George A. Constantinides

In this paper, we apply the self-attention from the state-of-the-art Transformer in Attention Is All You Need for the first time to a data-driven operator learning problem related to partial differential equations. An effort is put together…

Machine Learning · Computer Science 2021-11-02 Shuhao Cao