English
Related papers

Related papers: Efficient Dynamic Structured Sparse Training with …

200 papers

Although sparse neural networks have been studied extensively, the focus has been primarily on accuracy. In this work, we focus instead on network structure, and analyze three popular algorithms. We first measure performance when structure…

Machine Learning · Computer Science 2020-12-02 Maxwell Van Gelder , Mitchell Wortsman , Kiana Ehsani

We present a comprehensive framework for structured sparse coding and modeling extending the recent ideas of using learnable fast regressors to approximate exact sparse codes. For this purpose, we develop a novel block-coordinate proximal…

Machine Learning · Computer Science 2012-06-22 Alex Bronstein , Pablo Sprechmann , Guillermo Sapiro

Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured…

Machine Learning · Computer Science 2026-04-30 Younes Hourri , Mohammad Mozaffari , Maryam Mehri Dehnavi

The brain, as the source of inspiration for Artificial Neural Networks (ANN), is based on a sparse structure. This sparse structure helps the brain to consume less energy, learn easier and generalize patterns better than any other ANN. In…

Machine Learning · Computer Science 2021-03-16 Seyed Majid Naji , Azra Abtahi , Farokh Marvasti

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-01 Cong Guo , Bo Yang Hsueh , Jingwen Leng , Yuxian Qiu , Yue Guan , Zehuan Wang , Xiaoying Jia , Xipeng Li , Minyi Guo , Yuhao Zhu

In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Yongming Rao , Zuyan Liu , Wenliang Zhao , Jie Zhou , Jiwen Lu

Model ensembles have long been a cornerstone for improving generalization and robustness in deep learning. However, their effectiveness often comes at the cost of substantial computational overhead. To address this issue, state-of-the-art…

The redundancy of Convolutional neural networks not only depends on weights but also depends on inputs. Shuffling is an efficient operation for mixing channel information but the shuffle order is usually pre-defined. To reduce the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Kaijun Gong , Zhuowen Yin , Yushu Li , Kailing Guo , Xiangmin Xu

Pre-trained Transformers inherently possess the characteristic of sparse activation, where only a small fraction of the neurons are activated for each token. While sparse activation has been explored through post-training methods, its…

Computation and Language · Computer Science 2024-10-07 Zhengyan Zhang , Chaojun Xiao , Qiujieli Qin , Yankai Lin , Zhiyuan Zeng , Xu Han , Zhiyuan Liu , Ruobing Xie , Maosong Sun , Jie Zhou

As deep learning models grow, sparsity is becoming an increasingly critical component of deep neural networks, enabling improved performance and reduced storage. However, existing frameworks offer poor support for sparsity. Specialized…

Machine Learning · Computer Science 2023-04-18 Andrei Ivanov , Nikoli Dryden , Tal Ben-Nun , Saleh Ashkboos , Torsten Hoefler

We present a cosmology analysis of simulated weak lensing convergence maps using the Neural Field Scattering Transform (NFST) to constrain cosmological parameters. The NFST extends the Wavelet Scattering Transform (WST) by incorporating…

Cosmology and Nongalactic Astrophysics · Physics 2025-06-11 Matthew Craigie , Yuan-Sen Ting , Rossana Ruggeri , Tamara M. Davis

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…

Sparse neural networks are becoming increasingly important as the field seeks to improve the performance of existing models by scaling them up, while simultaneously trying to reduce power consumption and computational footprint.…

Machine Learning · Computer Science 2021-06-08 Siddhant M. Jayakumar , Razvan Pascanu , Jack W. Rae , Simon Osindero , Erich Elsen

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer…

Machine Learning · Computer Science 2025-06-23 Guozheng Ma , Lu Li , Zilin Wang , Li Shen , Pierre-Luc Bacon , Dacheng Tao

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast…

Neural and Evolutionary Computing · Computer Science 2020-09-04 Tsendsuren Munkhdalai

In this paper, we propose embedding sparsity into the structure of deep neural networks, where model parameters can be exactly zero during training with the stochastic gradient descent. Thus, it can learn the sparsified structure and the…

Machine Learning · Computer Science 2020-06-25 Yongjin Lee

Dense linear layers are the dominant computational bottleneck in foundation models. Identifying more efficient alternatives to dense matrices has enormous potential for building more compute-efficient models, as exemplified by the success…

Machine Learning · Computer Science 2024-06-11 Shikai Qiu , Andres Potapczynski , Marc Finzi , Micah Goldblum , Andrew Gordon Wilson

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during…

Machine Learning · Statistics 2018-10-23 Peter Bloem
‹ Prev 1 3 4 5 6 7 10 Next ›