English
Related papers

Related papers: Improving Neural Network Generalization by Combini…

200 papers

The training process of Deep Neural Network (DNN) is compute-intensive, often taking days to weeks to train a DNN model. Therefore, parallel execution of DNN training on GPUs is a widely adopted approach to speed up the process nowadays.…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-29 Chi-Chung Chen , Chia-Lin Yang , Hsiang-Yun Cheng

Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introduces several practical metrics including variance under…

Machine Learning · Computer Science 2025-07-17 Ahmed Salah , David Yevick

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Machine Learning · Computer Science 2019-12-02 Julia El Zini , Yara Rizk , Mariette Awad

We study dropout regularization in continuous-time models through the lens of random-batch methods -- a family of stochastic sampling schemes originally devised to reduce the computational cost of interacting particle systems. We construct…

Machine Learning · Computer Science 2025-10-16 Antonio Álvarez-López , Martín Hernández

Because most optimisations to achieve higher computational performance eventually are limited, parallelism that scales is required. Parallelised hardware alone is not sufficient, but software that matches the architecture is required to…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-07-11 Oskar Schirmer

Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while attempting to…

Machine Learning · Computer Science 2022-02-08 Dingzhu Wen , Ki-Jun Jeon , Kaibin Huang

Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Mateusz Michalkiewicz , Masoud Faraki , Xiang Yu , Manmohan Chandraker , Mahsa Baktashmotlagh

Pre-training large neural networks at scale imposes heavy memory demands on accelerators and often requires costly communication. We introduce Subnetwork Data Parallelism (SDP), a distributed training framework that partitions a model into…

Machine Learning · Computer Science 2025-10-06 Vaibhav Singh , Zafir Khalid , Edouard Oyallon , Eugene Belilovsky

I present a new way to parallelize the training of convolutional neural networks across multiple GPUs. The method scales significantly better than all alternatives when applied to modern convolutional neural networks.

Neural and Evolutionary Computing · Computer Science 2014-04-29 Alex Krizhevsky

Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Alex Hernández-García , Peter König

The focus of my PhD thesis is on exploring parallel approaches to efficiently solve problems modeled by constraints and presenting a new proposal. Current solvers are very advanced; they are carefully designed to effectively manage the…

Artificial Intelligence · Computer Science 2019-09-23 Fabio Tardivo

I introduce a new distributed system for effective training and regularizing of Large-Scale Neural Networks on distributed computing architectures. The experiments demonstrate the effectiveness of flexible model partitioning and…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-02-28 Edward J. Yoon

CNNs achieve remarkable performance by leveraging deep, over-parametrized architectures, trained on large datasets. However, they have limited generalization ability to data outside the training domain, and a lack of robustness to noise and…

Enhancing the generalisation abilities of neural networks (NNs) through integrating noise such as MixUp or Dropout during training has emerged as a powerful and adaptable technique. Despite the proven efficacy of noise in NN training, there…

Machine Learning · Computer Science 2024-04-04 Martin Ferianc , Ondrej Bohdal , Timothy Hospedales , Miguel Rodrigues

In this paper, we have investigated recurrent deep neural networks (DNNs) in combination with regularization techniques as dropout, zoneout, and regularization post-layer. As a benchmark, we chose the TIMIT phone recognition task due to its…

Computation and Language · Computer Science 2018-06-20 Jan Vanek , Josef Michalek , Josef Psutka

To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-23 Ziyue Luo , Xiaodong Yi , Guoping Long , Shiqing Fan , Chuan Wu , Jun Yang , Wei Lin

Graph neural networks (GNNs) are processing architectures that exploit graph structural information to model representations from network data. Despite their success, GNNs suffer from sub-optimal generalization performance given limited…

Machine Learning · Computer Science 2021-06-08 Zhan Gao , Subhrajit Bhattacharya , Leiming Zhang , Rick S. Blum , Alejandro Ribeiro , Brian M. Sadler

One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of…

Machine Learning · Computer Science 2016-06-13 Michael Cogswell , Faruk Ahmed , Ross Girshick , Larry Zitnick , Dhruv Batra

Parallel computing can offer an enormous advantage regarding the performance for very large applications in almost any field: scientific computing, computer vision, databases, data mining, and economics. GPUs are high performance many-core…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-24 Bogdan Oancea , Tudorel Andrei , Raluca Mariana Dragoescu

Deep neural networks, and in particular recurrent networks, are promising candidates to control autonomous agents that interact in real-time with the physical world. However, this requires a seamless integration of temporal features into…

Machine Learning · Statistics 2018-11-05 Volker Fischer , Jan Köhler , Thomas Pfeil