English
Related papers

Related papers: Subformer: Exploring Weight Sharing for Parameter …

200 papers

Large Language Models (LLMs) have achieved remarkable breakthroughs. However, the huge number of parameters in LLMs require significant amount of memory storage in inference, which prevents their practical deployment in many applications.…

Computation and Language · Computer Science 2024-10-08 Jingcun Wang , Yu-Guang Chen , Ing-Chao Lin , Bing Li , Grace Li Zhang

Time series forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies. This paper presents a novel transformer architecture for time series forecasting,…

Machine Learning · Computer Science 2025-02-12 Yanlong Wang , Jian Xu , Fei Ma , Shao-Lun Huang , Danny Dongning Sun , Xiao-Ping Zhang

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Machine Learning · Computer Science 2025-03-04 Jeffrey Gu , Serena Yeung-Levy

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

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

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensembles, work well, but are expensive in terms of memory and…

Machine Learning · Computer Science 2024-12-23 Albert Manuel Orozco Camacho , Stefan Horoi , Guy Wolf , Eugene Belilovsky

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to…

Machine Learning · Computer Science 2019-09-05 Byungsoo Kim , Vinicius C. Azevedo , Nils Thuerey , Theodore Kim , Markus Gross , Barbara Solenthaler

Standard neural networks are often overconfident when presented with data outside the training distribution. We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters. HyperGAN does not require…

Machine Learning · Computer Science 2020-07-16 Neale Ratzlaff , Li Fuxin

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in…

Machine Learning · Computer Science 2024-12-30 Chongjie Si , Xiaokang Yang , Wei Shen

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

Many deep learning applications benefit from using large models with billions of parameters. Training these models is notoriously expensive due to the need for specialized HPC clusters. In this work, we consider alternative setups for…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-30 Max Ryabinin , Tim Dettmers , Michael Diskin , Alexander Borzunov

Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths. In this work, we train a neural network that serves as a hypernetwork,…

Machine Learning · Statistics 2019-05-09 Lior Deutsch , Erik Nijkamp , Yu Yang

Exploiting the great expressive power of Deep Neural Network architectures, relies on the ability to train them. While current theoretical work provides, mostly, results showing the hardness of this task, empirical evidence usually differs…

Machine Learning · Computer Science 2017-06-05 Shai Shalev-Shwartz , Ohad Shamir , Shaked Shammah

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Anantha Padmanaban Krishna Kumar

We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead…

Machine Learning · Computer Science 2019-02-26 Pramod Kaushik Mudrakarta , Mark Sandler , Andrey Zhmoginov , Andrew Howard

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

This paper proposes a novel learning method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by using parameter sharing. However, sharing parameters between unrelated tasks can…

Machine Learning · Computer Science 2020-07-21 Krzysztof Maziarz , Efi Kokiopoulou , Andrea Gesmundo , Luciano Sbaiz , Gabor Bartok , Jesse Berent

Transformer has been widely used thanks to its ability to capture sequence information in an efficient way. However, recent developments, such as BERT and GPT-2, deliver only heavy architectures with a focus on effectiveness. In this paper,…

Computation and Language · Computer Science 2020-02-17 Chenguang Wang , Zihao Ye , Aston Zhang , Zheng Zhang , Alexander J. Smola

Large-scale Transformer models are known for their exceptional performance in a range of tasks, but training them can be difficult due to the requirement for communication-intensive model parallelism. One way to improve training speed is to…

Machine Learning · Computer Science 2023-01-09 Song Bian , Dacheng Li , Hongyi Wang , Eric P. Xing , Shivaram Venkataraman

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power…

Computation and Language · Computer Science 2020-09-22 Zhaojiang Lin , Andrea Madotto , Pascale Fung
‹ Prev 1 3 4 5 6 7 10 Next ›