English
Related papers

Related papers: Reducing Transformer Depth on Demand with Structur…

200 papers

Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training…

Information Theory · Computer Science 2026-02-03 Sijing Xie , Dingzhu Wen , Changsheng You , Qimei Chen , Mehdi Bennis , Kaibin Huang

Dropout regularization has been widely used in deep learning but performs less effective for convolutional neural networks since the spatially correlated features allow dropped information to still flow through the networks. Some structured…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Hui Zhu , Xiaofang Zhao

Deep Neural Networks often require good regularizers to generalize well. Dropout is one such regularizer that is widely used among Deep Learning practitioners. Recent work has shown that Dropout can also be viewed as performing Approximate…

Machine Learning · Computer Science 2016-11-22 Suraj Srinivas , R. Venkatesh Babu

Overfitting is a well-known issue extending even to state-of-the-art (SOTA) Machine Learning (ML) models, resulting in reduced generalization, and a significant train-test performance gap. Mitigation measures include a combination of…

Machine Learning · Computer Science 2025-05-29 Shreyas Gururaj , Lars Grüne , Wojciech Samek , Sebastian Lapuschkin , Leander Weber

Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed…

Computer Vision and Pattern Recognition · Computer Science 2014-03-11 Vu Pham , Théodore Bluche , Christopher Kermorvant , Jérôme Louradour

Text embeddings, i.e. vector representations of entire texts, play an important role in many NLP applications, such as retrieval-augmented generation, clustering, or visualizing collections of texts for data exploration. Currently,…

Computation and Language · Computer Science 2026-03-17 Rita González-Márquez , Philipp Berens , Dmitry Kobak

Depth pruning aims to reduce the inference cost of a large language model without any hardware-specific complications, by simply removing several less important transformer blocks. However, our empirical findings suggest that the importance…

Computation and Language · Computer Science 2025-06-13 Juyun Wee , Minjae Park , Jaeho Lee

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it…

Computer Vision and Pattern Recognition · Computer Science 2016-07-05 Wei Pan , Hao Dong , Yike Guo

With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model…

Computation and Language · Computer Science 2024-05-28 Sheng Wang , Liheng Chen , Jiyue Jiang , Boyang Xue , Lingpeng Kong , Chuan Wu

Dropout is a very effective method in preventing overfitting and has become the go-to regularizer for multi-layer neural networks in recent years. Hierarchical mixture of experts is a hierarchically gated model that defines a soft decision…

Machine Learning · Computer Science 2018-12-27 Ozan İrsoy , Ethem Alpaydın

Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pruning methods do not provide any performance guarantees, and…

Machine Learning · Computer Science 2023-02-14 Marwa El Halabi , Suraj Srinivas , Simon Lacoste-Julien

Curating foundation speech models for edge and IoT settings, where computational resources vary over time, requires dynamic architectures featuring adaptable reduction strategies. One emerging approach is layer dropping ($\mathcal{LD}$)…

Sound · Computer Science 2025-07-11 Abdul Hannan , Daniele Falavigna , Alessio Brutti

Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Golnaz Ghiasi , Tsung-Yi Lin , Quoc V. Le

Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few. In lockstep, regularization methods, which aim to prevent…

Machine Learning · Computer Science 2020-07-28 Claudio Filipi Goncalves do Santos , Danilo Colombo , Mateus Roder , João Paulo Papa

Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular…

Machine Learning · Computer Science 2018-06-27 Poorya Mianjy , Raman Arora , Rene Vidal

Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A…

Machine Learning · Statistics 2018-03-29 Konrad Zolna , Devansh Arpit , Dendi Suhubdy , Yoshua Bengio

Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large and redundant network, and then determines which units…

Computer Vision and Pattern Recognition · Computer Science 2019-09-30 Yulong Wang , Xiaolu Zhang , Lingxi Xie , Jun Zhou , Hang Su , Bo Zhang , Xiaolin Hu

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes their usage costly,…

Computation and Language · Computer Science 2021-03-30 Ziheng Wang , Jeremy Wohlwend , Tao Lei