English
Related papers

Related papers: Compression via Pre-trained Transformers: A Study …

200 papers

We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the…

Image and Video Processing · Electrical Eng. & Systems 2023-06-26 Ties van Rozendaal , Johann Brehmer , Yunfan Zhang , Reza Pourreza , Auke Wiggers , Taco S. Cohen

The number of mobile robots with constrained computing resources that need to execute complex machine learning models has been increasing during the past decade. Commonly, these robots rely on edge infrastructure accessible over wireless…

Machine Learning · Computer Science 2022-07-22 Timotheos Souroulla , Alberto Hata , Ahmad Terra , Özer Özkahraman , Rafia Inam

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Machine Learning · Computer Science 2026-03-16 Krishu K Thapa , Reet Barik , Krishna Teja Chitty-Venkata , Murali Emani , Venkatram Vishwanath

Although pretrained language models can be fine-tuned to produce state-of-the-art results for a very wide range of language understanding tasks, the dynamics of this process are not well understood, especially in the low data regime. Why…

Machine Learning · Computer Science 2020-12-25 Armen Aghajanyan , Luke Zettlemoyer , Sonal Gupta

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performance conceals…

Machine Learning · Computer Science 2021-09-07 Sara Hooker , Aaron Courville , Gregory Clark , Yann Dauphin , Andrea Frome

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…

Computation and Language · Computer Science 2022-08-16 Hassan Sajjad , Fahim Dalvi , Nadir Durrani , Preslav Nakov

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

Machine Learning · Computer Science 2020-04-08 Matan Haroush , Itay Hubara , Elad Hoffer , Daniel Soudry

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

In this paper, we propose a novel variable-rate learned image compression framework with a conditional autoencoder. Previous learning-based image compression methods mostly require training separate networks for different compression rates…

Image and Video Processing · Electrical Eng. & Systems 2019-09-12 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

Existing ML models are known to be highly over-parametrized, and use significantly more resources than required for a given task. Prior work has explored compressing models offline, such as by distilling knowledge from larger models into…

Machine Learning · Computer Science 2022-05-17 Julian Knodt

Federated Learning (FL) incurs high communication overhead, which can be greatly alleviated by compression for model updates. Yet the tradeoff between compression and model accuracy in the networked environment remains unclear and, for…

Machine Learning · Computer Science 2021-12-14 Laizhong Cui , Xiaoxin Su , Yipeng Zhou , Jiangchuan Liu

Reducing the data footprint of visual content via image compression is essential to reduce storage requirements, but also to reduce the bandwidth and latency requirements for transmission. In particular, the use of compressed images allows…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 João Maria Janeiro , Stanislav Frolov , Alaaeldin El-Nouby , Jakob Verbeek

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…

Machine Learning · Computer Science 2021-07-28 Danielle Rothermel , Margaret Li , Tim Rocktäschel , Jakob Foerster

Large language models, which are often trained for hundreds of thousands of compute days, have shown remarkable capabilities for zero- and few-shot learning. Given their computational cost, these models are difficult to replicate without…

As the number of pre-trained machine learning (ML) models is growing exponentially, data reduction tools are not catching up. Existing data reduction techniques are not specifically designed for pre-trained model (PTM) dataset files. This…

Databases · Computer Science 2024-03-12 Zhaoyuan Su , Ammar Ahmed , Zirui Wang , Ali Anwar , Yue Cheng

Besides accuracy, the model size of convolutional neural networks (CNN) models is another important factor considering limited hardware resources in practical applications. For example, employing deep neural networks on mobile systems…

Machine Learning · Computer Science 2021-07-05 Huixin Zhan , Wei-Ming Lin , Yongcan Cao

With the rise of Transformers as the standard for language processing, and their advancements in computer vision, there has been a corresponding growth in parameter size and amounts of training data. Many have come to believe that because…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Ali Hassani , Steven Walton , Nikhil Shah , Abulikemu Abuduweili , Jiachen Li , Humphrey Shi

State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs,…

Computation and Language · Computer Science 2024-07-25 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Fine-tuning Large Language Models (LLMs) and storing them for each downstream task or domain is impractical because of the massive model size (e.g., 350GB in GPT-3). Current literature, such as LoRA, showcases the potential of low-rank…

Computation and Language · Computer Science 2024-05-01 Soroush Abbasi Koohpayegani , KL Navaneet , Parsa Nooralinejad , Soheil Kolouri , Hamed Pirsiavash