English
Related papers

Related papers: Towards the Connection between Activation Sparsity…

200 papers

Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Andy Li , Aiden Durrant , Milan Markovic , Tianjin Huang , Souvik Kundu , Tianlong Chen , Lu Yin , Georgios Leontidis

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

Computation and Language · Computer Science 2021-10-07 Biao Zhang , Ivan Titov , Rico Sennrich

The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer. Consequently, a lengthy sequence of algorithm…

Machine Learning · Computer Science 2016-05-11 Bo Xin , Yizhou Wang , Wen Gao , David Wipf

Deep and wide neural networks successfully fit very complex functions today, but dense models are starting to be prohibitively expensive for inference. To mitigate this, one promising direction is networks that activate a sparse subgraph of…

Machine Learning · Computer Science 2022-08-10 Cenk Baykal , Nishanth Dikkala , Rina Panigrahy , Cyrus Rashtchian , Xin Wang

It is well known that direct training of deep neural networks will generally lead to poor results. A major progress in recent years is the invention of various pretraining methods to initialize network parameters and it was shown that such…

Machine Learning · Computer Science 2014-06-10 Jun Li , Wei Luo , Jian Yang , Xiaotong Yuan

That neural networks may be pruned to high sparsities and retain high accuracy is well established. Recent research efforts focus on pruning immediately after initialization so as to allow the computational savings afforded by sparsity to…

Machine Learning · Computer Science 2022-01-28 Ilan Price , Jared Tanner

Resource efficiency plays an important role for machine learning nowadays. The energy and decision latency are two critical aspects to ensure a sustainable and practical application. Unfortunately, the energy consumption and decision…

Cryptography and Security · Computer Science 2024-03-28 Andreas Müller , Erwin Quiring

Artificial neural networks open up unprecedented machine learning capabilities at the cost of ever growing computational requirements. Sparsifying the parameters, often achieved through weight pruning, has been identified as a powerful…

Machine Learning · Computer Science 2024-11-28 Rishav Mukherji , Mark Schöne , Khaleelulla Khan Nazeer , Christian Mayr , Anand Subramoney

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that…

Machine Learning · Computer Science 2025-06-04 Kang Zhao , Tao Yuan , Han Bao , Zhenfeng Su , Chang Gao , Zhaofeng Sun , Zichen Liang , Liping Jing , Jianfei Chen

We study the emergence of sparse representations in neural networks. We show that in unsupervised models with regularization, the emergence of sparsity is the result of the input data samples being distributed along highly non-linear or…

Machine Learning · Computer Science 2019-03-08 Vivek Bakaraju , Kishore Reddy Konda

As the context window expands, self-attention increasingly dominates the transformer's inference time. Therefore, accelerating attention computation while minimizing performance degradation is essential for the efficient deployment of Large…

Computation and Language · Computer Science 2025-03-14 Eli Sason , Darya Frolova , Boris Nazarov , Felix Goldberd

In this work, we systematically investigate the efficacy of dynamic activation mechanisms within the LLaMA family of language models. Despite the potential of dynamic activation methods to reduce computation and increase speed in models…

Machine Learning · Computer Science 2024-05-16 Chi Ma , Mincong Huang , Chao Wang , Yujie Wang , Lei Yu

This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Yunsheng Li , Yinpeng Chen , Xiyang Dai , Dongdong Chen , Mengchen Liu , Lu Yuan , Zicheng Liu , Lei Zhang , Nuno Vasconcelos

Dedicated neural network (NN) architectures have been designed to handle specific data types (such as CNN for images or RNN for text), which ranks them among state-of-the-art methods for dealing with these data. Unfortunately, no…

Machine Learning · Statistics 2022-10-03 Patrick Lutz , Ludovic Arnould , Claire Boyer , Erwan Scornet

The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Nathan Hubens , Victor Delvigne , Matei Mancas , Bernard Gosselin , Marius Preda , Titus Zaharia

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

Machine Learning · Computer Science 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an…

Machine Learning · Computer Science 2018-06-05 Maohua Zhu , Jason Clemons , Jeff Pool , Minsoo Rhu , Stephen W. Keckler , Yuan Xie

Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the training loss, and thus a…

Machine Learning · Computer Science 2023-07-25 Kaiyue Wen , Zhiyuan Li , Tengyu Ma

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu