English
Related papers

Related papers: Understanding and Exploiting Weight Update Sparsit…

200 papers

As the size of datasets used in statistical learning continues to grow, distributed training of models has attracted increasing attention. These methods partition the data and exploit parallelism to reduce memory and runtime, but suffer…

Machine Learning · Computer Science 2024-07-10 Fred Lu , Ryan R. Curtin , Edward Raff , Francis Ferraro , James Holt

Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices. Unfortunately, current deep networks remain not only too compute-heavy for inference and training on edge devices,…

Machine Learning · Computer Science 2021-12-21 Sameer Bibikar , Haris Vikalo , Zhangyang Wang , Xiaohan Chen

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic…

Machine Learning · Computer Science 2025-02-10 Chris Kolb , Tobias Weber , Bernd Bischl , David Rügamer

An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models or the learning of word-embeddings, often posed as…

Neural and Evolutionary Computing · Computer Science 2015-07-15 Pascal Vincent , Alexandre de Brébisson , Xavier Bouthillier

Training on edge devices enables personalized model fine-tuning to enhance real-world performance and maintain data privacy. However, the gradient computation for backpropagation in the training requires significant memory buffers to store…

Hardware Architecture · Computer Science 2025-03-25 I-Hsuan Li , Tian-Sheuan Chang

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Machine Learning · Computer Science 2026-01-29 Longteng Zhang , Sen Wu , Shuai Hou , Zhengyu Qing , Zhuo Zheng , Danning Ke , Qihong Lin , Qiang Wang , Shaohuai Shi , Xiaowen Chu

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

Synchronous stochastic gradient descent (SGD) is the most common method used for distributed training of deep learning models. In this algorithm, each worker shares its local gradients with others and updates the parameters using the…

Machine Learning · Computer Science 2020-09-22 Negar Foroutan Eghlidi , Martin Jaggi

Semi-structured sparsity provides a practical path to accelerate large language models (LLMs) with native hardware support, but post-training semi-structured pruning often suffers from substantial quality degradation due to strong…

Machine Learning · Computer Science 2026-05-08 Liu Hanzuo , Chaofan Lin , Weixuan Sun , Yulong Wang , Key , Rayying , Mingyu Gao

We propose SLoPe, a Double-Pruned Sparse Plus Lazy Low-rank Adapter Pretraining method for LLMs that improves the accuracy of sparse LLMs while accelerating their pretraining and inference and reducing their memory footprint. Sparse…

Machine Learning · Computer Science 2025-01-28 Mohammad Mozaffari , Amir Yazdanbakhsh , Zhao Zhang , Maryam Mehri Dehnavi

This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept…

Machine Learning · Computer Science 2024-03-01 Mohamad Mestoukirdi , Omid Esrafilian , David Gesbert , Qianrui Li , Nicolas Gresset

Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication…

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost…

Machine Learning · Computer Science 2024-06-11 Weixi Song , Zuchao Li , Lefei Zhang , Hai Zhao , Bo Du

Large-scale deep neural networks (DNN) exhibit excellent performance for various tasks. As DNNs and datasets grow, distributed training becomes extremely time-consuming and demands larger clusters. A main bottleneck is the resulting…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-27 Yisu Wang , Ruilong Wu , Xinjiao Li , Dirk Kutscher

Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to…

Neural and Evolutionary Computing · Computer Science 2019-05-10 Brian Crafton , Abhinav Parihar , Evan Gebhardt , Arijit Raychowdhury

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

Radio frequency sources are observed at a fusion center via sensor measurements made over slow flat-fading channels. The number of sources may be larger than the number of sensors, but their activity is sparse and intermittent with bursty…

Signal Processing · Electrical Eng. & Systems 2019-08-07 Annan Dong , Osvaldo Simeone , Alexander Haimovich , Jason Dabin

We consider sparsity-based techniques for the approximation of high-dimensional functions from random pointwise evaluations. To date, almost all the works published in this field contain some a priori assumptions about the error corrupting…

Numerical Analysis · Mathematics 2019-05-10 Ben Adcock , Anyi Bao , Simone Brugiapaglia

Current pre-trained language model approaches to information retrieval can be broadly divided into two categories: sparse retrievers (to which belong also non-neural approaches such as bag-of-words methods, e.g., BM25) and dense retrievers.…

Information Retrieval · Computer Science 2022-05-03 Hang Li , Shuai Wang , Shengyao Zhuang , Ahmed Mourad , Xueguang Ma , Jimmy Lin , Guido Zuccon