English
Related papers

Related papers: On the Duality between Gradient Transformations an…

200 papers

In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers. Since the…

Machine Learning · Computer Science 2022-02-04 Daniel Bershatsky , Aleksandr Mikhalev , Alexandr Katrutsa , Julia Gusak , Daniil Merkulov , Ivan Oseledets

The memory challenges associated with training Large Language Models (LLMs) have become a critical concern, particularly when using the Adam optimizer. To address this issue, numerous memory-efficient techniques have been proposed, with…

Machine Learning · Computer Science 2025-02-12 Yiming Chen , Yuan Zhang , Yin Liu , Kun Yuan , Zaiwen Wen

Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradients for efficient parameter updates. The aggregated history of gradients nudges the parameter…

Machine Learning · Computer Science 2021-06-22 Paul-Aymeric McRae , Prasanna Parthasarathi , Mahmoud Assran , Sarath Chandar

Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…

Machine Learning · Computer Science 2024-12-16 Piotr Teterwak , Kate Saenko , Bryan A. Plummer , Ser-Nam Lim

Training large language models (LLMs) relies on adaptive optimizers such as Adam, which introduce extra operations and require significantly more memory to maintain first- and second-order moments than SGD. While recent works such as…

Machine Learning · Computer Science 2026-05-22 Athanasios Glentis , Jiaxiang Li , Andi Han , Mingyi Hong

State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network layers on top of…

Computation and Language · Computer Science 2022-05-04 Nafise Sadat Moosavi , Quentin Delfosse , Kristian Kersting , Iryna Gurevych

Adaptive gradient-based optimizers such as Adagrad and Adam are crucial for achieving state-of-the-art performance in machine translation and language modeling. However, these methods maintain second-order statistics for each parameter,…

Machine Learning · Computer Science 2019-09-13 Rohan Anil , Vineet Gupta , Tomer Koren , Yoram Singer

The advent of the transformer has sparked a quick growth in the size of language models, far outpacing hardware improvements. (Dense) transformers are expected to reach the trillion-parameter scale in the near future, for which training…

Machine Learning · Computer Science 2021-06-08 Joel Lamy-Poirier

Parameter-efficient tuning methods such as LoRA could achieve comparable performance to model tuning by tuning a small portion of the parameters. However, substantial computational resources are still required, as this process involves…

Computation and Language · Computer Science 2024-03-05 Feihu Jin , Yin Liu , Ying Tan

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches are reparameterization methods, which update a target…

Machine Learning · Computer Science 2025-10-27 Aymane El Firdoussi , El Mahdi Chayti , Mohamed El Amine Seddik , Martin Jaggi

Training Large Language Models (LLMs) presents significant memory challenges, predominantly due to the growing size of weights and optimizer states. Common memory-reduction approaches, such as low-rank adaptation (LoRA), add a trainable…

Machine Learning · Computer Science 2024-06-04 Jiawei Zhao , Zhenyu Zhang , Beidi Chen , Zhangyang Wang , Anima Anandkumar , Yuandong Tian

The widespread utilization of language models in modern applications is inconceivable without Parameter-Efficient Fine-Tuning techniques, such as low-rank adaptation ($\texttt{LoRA}$), which adds trainable adapters to selected layers.…

Machine Learning · Computer Science 2025-10-17 Andrey Veprikov , Vladimir Solodkin , Alexander Zyl , Andrey Savchenko , Aleksandr Beznosikov

Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. However, there exists a gap in understanding how…

Machine Learning · Computer Science 2023-03-08 Alexander Detkov , Mohammad Salameh , Muhammad Fetrat Qharabagh , Jialin Zhang , Wei Lui , Shangling Jui , Di Niu

Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a…

Computation and Language · Computer Science 2021-06-08 Ruidan He , Linlin Liu , Hai Ye , Qingyu Tan , Bosheng Ding , Liying Cheng , Jia-Wei Low , Lidong Bing , Luo Si

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by training small…

Information Retrieval · Computer Science 2023-03-24 Vaishali Pal , Carlos Lassance , Hervé Déjean , Stéphane Clinchant

Gradient-free optimizers allow for tackling problems regardless of the smoothness or differentiability of their objective function, but they require many more iterations to converge when compared to gradient-based algorithms. This has made…

Machine Learning · Computer Science 2024-09-24 Gawel Kus , Miguel A. Bessa

Given a differentiable network architecture and loss function, we revisit optimizing the network's neurons in function space using Boosted Backpropagation (Grubb & Bagnell, 2010), in contrast to optimizing in parameter space. From this…

Machine Learning · Computer Science 2025-02-04 Daniel Munoz

Parameter-efficient fine-tuning optimizes large, pre-trained foundation models by updating a subset of parameters; in this class, Low-Rank Adaptation (LoRA) is particularly effective. Inspired by an effort to investigate the different roles…

Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework…

Computation and Language · Computer Science 2025-12-11 Salvador Carrión , Francisco Casacuberta

Despite the dominance and effectiveness of scaling, resulting in large networks with hundreds of billions of parameters, the necessity to train overparameterized models remains poorly understood, while training costs grow exponentially. In…

Computation and Language · Computer Science 2023-12-12 Vladislav Lialin , Namrata Shivagunde , Sherin Muckatira , Anna Rumshisky
‹ Prev 1 2 3 10 Next ›