English
Related papers

Related papers: ReLU Strikes Back: Exploiting Activation Sparsity …

200 papers

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

Activation function is crucial to the recent successes of deep neural networks. In this paper, we first propose a new activation function, Multiple Parametric Exponential Linear Units (MPELU), aiming to generalize and unify the rectified…

Computer Vision and Pattern Recognition · Computer Science 2017-01-18 Yang Li , Chunxiao Fan , Yong Li , Qiong Wu , Yue Ming

Recently, large language models (LLMs) have achieved tremendous breakthroughs in the field of NLP, but still lack understanding of their internal neuron activities when processing different languages. We designed a method to convert dense…

Computation and Language · Computer Science 2024-10-08 Weize Liu , Yinlong Xu , Hongxia Xu , Jintai Chen , Xuming Hu , Jian Wu

While scaling laws have been continuously validated in large language models (LLMs) with increasing model parameters, the inherent tension between the inference demands of LLMs and the limited resources of edge devices poses a critical…

The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands. Pruning has emerged as a pivotal compression strategy, introducing sparsity…

Computation and Language · Computer Science 2024-11-04 Guangji Bai , Yijiang Li , Chen Ling , Kibaek Kim , Liang Zhao

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous…

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger…

Machine Learning · Computer Science 2026-02-09 Meghana Madhyastha , Daniel Haziza , Jesse Cai , Newsha Ardalani , Zhiqi Bu , Carole-Jean Wu

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Machine Learning · Computer Science 2025-11-05 Daman Arora , Andrea Zanette

The discovery of the lazy neuron phenomenon in trained Transformers, where the vast majority of neurons in their feed-forward networks (FFN) are inactive for each token, has spurred tremendous interests in activation sparsity for enhancing…

Rectified linear units, or ReLUs, have become the preferred activation function for artificial neural networks. In this paper we consider two basic learning problems assuming that the underlying data follow a generative model based on a…

Machine Learning · Statistics 2018-03-13 Arya Mazumdar , Ankit Singh Rawat

Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive or "dead" neurons caused by its hard zero cutoff. To address…

Machine Learning · Computer Science 2025-11-12 Md Motaleb Hossen Manik , Md Zabirul Islam , Ge Wang

In contemporary large language models (LLMs), the swish-gated linear unit (SwiGLU) activation function is widely adopted to regulate the information flow and introduce non-linearity. For large positive inputs, SwiGLU approximates the…

Computation and Language · Computer Science 2026-05-26 Peijie Jiang , Yuqi Feng , Cunyin Peng , Qian Zhao , Jia Liu , KunLong Chen , Zhiqiang Zhang , Jun Zhou

This paper studies the curious phenomenon for machine learning models with Transformer architectures that their activation maps are sparse. By activation map we refer to the intermediate output of the multi-layer perceptrons (MLPs) after a…

In neural networks, non-linearity is introduced by activation functions. One commonly used activation function is Rectified Linear Unit (ReLU). ReLU has been a popular choice as an activation but has flaws. State-of-the-art functions like…

Machine Learning · Computer Science 2021-12-23 Advait Vagerwal

Overwhelming theoretical and empirical evidence shows that mildly overparametrized neural networks -- those with more connections than the size of the training data -- are often able to memorize the training data with $100\%$ accuracy. This…

Machine Learning · Computer Science 2020-06-04 Roman Vershynin

Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive computational and memory demands. While lightweight LLMs have…

Machine Learning · Computer Science 2025-10-14 Tuowei Wang , Ruwen Fan , Minxing Huang , Zixu Hao , Kun Li , Ting Cao , Youyou Lu , Yaoxue Zhang , Ju Ren

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

Activation function is a key component in deep learning that performs non-linear mappings between the inputs and outputs. Rectified Linear Unit (ReLU) has been the most popular activation function across the deep learning community.…

Machine Learning · Computer Science 2022-03-01 Hock Hung Chieng , Noorhaniza Wahid , Pauline Ong

Large language models (LLMs) are limited by substantial computational cost. We introduce a "computational economics" framework that treats an LLM as an internal economy of resource-constrained agents (attention heads and neuron blocks) that…

Computation and Language · Computer Science 2025-12-30 Sandeep Reddy , Kabir Khan , Rohit Patil , Ananya Chakraborty , Faizan A. Khan , Swati Kulkarni , Arjun Verma , Neha Singh

In this paper, we consider robust nonparametric regression using deep neural networks with ReLU activation function. While several existing theoretically justified methods are geared towards robustness against identical heavy-tailed noise…

Methodology · Statistics 2023-11-01 Juntong Chen
‹ Prev 1 4 5 6 7 8 10 Next ›