English
Related papers

Related papers: Accelerated Large Batch Optimization of BERT Pretr…

200 papers

Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs), due to the large GPU memory requirement. To…

Machine Learning · Computer Science 2025-05-29 Dang Nguyen , Wenhan Yang , Rathul Anand , Yu Yang , Baharan Mirzasoleiman

Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of…

Machine Learning · Computer Science 2020-08-04 Rahul Yedida , Snehanshu Saha , Tejas Prashanth

While pre-training and fine-tuning, e.g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online…

Computation and Language · Computer Science 2020-04-28 Kaitao Song , Hao Sun , Xu Tan , Tao Qin , Jianfeng Lu , Hongzhi Liu , Tie-Yan Liu

We explore leveraging corpus-specific vocabularies that improve both efficiency and effectiveness of learned sparse retrieval systems. We find that pre-training the underlying BERT model on the target corpus, specifically targeting…

Information Retrieval · Computer Science 2024-01-15 Puxuan Yu , Antonio Mallia , Matthias Petri

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter…

Computation and Language · Computer Science 2023-08-08 Yang Luo , Xiaozhe Ren , Zangwei Zheng , Zhuo Jiang , Xin Jiang , Yang You

Supervised learning with large-scale data usually leads to complex optimization problems, especially for classification tasks with multiple classes. Stochastic subgradient methods can enable efficient learning with a large number of samples…

Machine Learning · Computer Science 2025-11-25 Kartheek Bondugula , Santiago Mazuelas , Aritz Pérez

Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training…

Computation and Language · Computer Science 2023-01-06 Luke Gessler , Amir Zeldes

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants…

Machine Learning · Computer Science 2025-09-22 Yuen Chen , Yian Wang , Hari Sundaram

In recent years, major advancements in natural language processing (NLP) have been driven by the emergence of large language models (LLMs), which have significantly revolutionized research and development within the field. Building upon…

Computation and Language · Computer Science 2023-05-09 Hazal Türkmen , Oğuz Dikenelli , Cenk Eraslan , Mehmet Cem Çallı , Süha Süreyya Özbek

The prohibitive training costs of Large Language Models (LLMs) have emerged as a significant bottleneck in the development of next-generation LLMs. In this paper, we show that it is possible to significantly reduce the training costs of…

Computation and Language · Computer Science 2025-05-16 Chenze Shao , Fandong Meng , Jie Zhou

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Yusuke Shinohara , Shinji Watanabe

We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less…

Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational…

Computation and Language · Computer Science 2021-07-13 Xiaotao Gu , Liyuan Liu , Hongkun Yu , Jing Li , Chen Chen , Jiawei Han

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Computation and Language · Computer Science 2025-10-20 Liang Wang , Nan Yang , Shaohan Huang , Li Dong , Furu Wei

Scheduling the batch size to increase is an effective strategy to control gradient noise when training deep neural networks. Current approaches implement scheduling heuristics that neglect structure within the optimization procedure,…

Machine Learning · Computer Science 2022-05-18 Calum Robert MacLellan , Feng Dong

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

Computation and Language · Computer Science 2022-09-28 Arnav Ladkat , Aamir Miyajiwala , Samiksha Jagadale , Rekha Kulkarni , Raviraj Joshi

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on…

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. A knowledge distillation approach addresses the computational efficiency by self-distilling BERT into a…

Computation and Language · Computer Science 2023-05-11 Shira Guskin , Moshe Wasserblat , Chang Wang , Haihao Shen

End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…

Computation and Language · Computer Science 2022-06-30 Pu Wang , Hugo Van hamme