English
Related papers

Related papers: FoundationLayerNorm: Scaling BERT and GPT to 1,000…

200 papers

In this paper, we propose a simple yet effective method to stabilize extremely deep Transformers. Specifically, we introduce a new normalization function (DeepNorm) to modify the residual connection in Transformer, accompanying with…

Computation and Language · Computer Science 2022-03-02 Hongyu Wang , Shuming Ma , Li Dong , Shaohan Huang , Dongdong Zhang , Furu Wei

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

Recently, DeepNorm scales Transformers into extremely deep (i.e., 1000 layers) and reveals the promising potential of deep scaling. To stabilize the training of deep models, DeepNorm (Wang et al., 2022) attempts to constrain the model…

Machine Learning · Computer Science 2023-05-05 Yijin Liu , Xianfeng Zeng , Fandong Meng , Jie Zhou

Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very…

Computation and Language · Computer Science 2020-11-30 Cheng Yang , Shengnan Wang , Chao Yang , Yuechuan Li , Ru He , Jingqiao Zhang

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different implementations for better performance, e.g., Post-LayerNorm…

Successfully training deep neural networks often requires either batch normalization, appropriate weight initialization, both of which come with their own challenges. We propose an alternative, geometrically motivated method for training.…

Machine Learning · Computer Science 2019-10-08 Aram-Alexandre Pooladian , Chris Finlay , Adam M Oberman

Large-scale Transformer models have significantly promoted the recent development of natural language processing applications. However, little effort has been made to unify the effective models. In this paper, driven by providing a new set…

Computation and Language · Computer Science 2022-04-12 Dezhou Shen

Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity has become a major obstacle when training deep GNNs for…

Machine Learning · Computer Science 2022-04-12 Guohao Li , Matthias Müller , Bernard Ghanem , Vladlen Koltun

Models based on BERT have been extremely successful in solving a variety of natural language processing (NLP) tasks. Unfortunately, many of these large models require a great deal of computational resources and/or time for pre-training and…

Computation and Language · Computer Science 2022-02-28 Sharath Nittur Sridhar , Anthony Sarah , Sairam Sundaresan

In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the Hessian matrix, and the maximum tolerable learning rate. We…

Machine Learning · Computer Science 2026-02-03 Marco Chen , Xianbiao Qi , Yelin He , Jiaquan Ye , Rong Xiao

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

Recent work in language modeling demonstrates that training large transformer models advances the state of the art in Natural Language Processing applications. However, very large models can be quite difficult to train due to memory…

Computation and Language · Computer Science 2020-03-17 Mohammad Shoeybi , Mostofa Patwary , Raul Puri , Patrick LeGresley , Jared Casper , Bryan Catanzaro

Fine-tuning a pre-trained model, such as Bidirectional Encoder Representations from Transformers (BERT), has been proven to be an effective method for solving many natural language processing (NLP) tasks. However, due to the large number of…

Computation and Language · Computer Science 2024-04-01 Taha ValizadehAslani , Hualou Liang

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy

Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the…

Machine Learning · Statistics 2016-07-22 Jimmy Lei Ba , Jamie Ryan Kiros , Geoffrey E. Hinton

The increasing size of large neural network models, specifically language models and foundational image models, poses deployment challenges, prompting efforts to reduce memory requirements and enhance computational efficiency. These efforts…

Machine Learning · Computer Science 2025-09-10 Eduardo Lobo Lustoda Cabral , Paulo Pirozelli , Larissa Driemeier

Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even…

Computation and Language · Computer Science 2021-12-20 Ofir Zafrir , Guy Boudoukh , Peter Izsak , Moshe Wasserblat

Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight…

Machine Learning · Computer Science 2019-10-17 Biao Zhang , Rico Sennrich

Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated Learning (FL) has been emerging as a method for privacy-preserving pooling of datasets employing…

Machine Learning · Computer Science 2023-03-21 Bruno Casella , Roberto Esposito , Antonio Sciarappa , Carlo Cavazzoni , Marco Aldinucci
‹ Prev 1 2 3 10 Next ›