English
Related papers

Related papers: Accelerated Training via Incrementally Growing Neu…

200 papers

Large neural networks pretrained on web-scale corpora are central to modern machine learning. In this paradigm, the distribution of the large, heterogeneous pretraining data rarely matches that of the application domain. This work considers…

Machine Learning · Computer Science 2023-11-21 David Grangier , Pierre Ablin , Awni Hannun

Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made.…

Computational Engineering, Finance, and Science · Computer Science 2025-07-30 D. Veerababu , Ashwin A. Raikar , Prasanta K. Ghosh

In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with…

Machine Learning · Computer Science 2021-05-12 Renlong Jie , Junbin Gao , Andrey Vasnev , Minh-Ngoc Tran

In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…

Machine Learning · Computer Science 2022-07-20 Zhiyuan Li , Srinadh Bhojanapalli , Manzil Zaheer , Sashank J. Reddi , Sanjiv Kumar

Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proportions within batches,…

Machine Learning · Computer Science 2025-10-24 Shyam Venkatasubramanian , Vahid Tarokh

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…

Machine Learning · Computer Science 2026-04-15 Amar Gahir , Varshil Patel , Shreyank N Gowda

This paper presents a comparative analysis of distributed training strategies for large-scale neural networks, focusing on data parallelism, model parallelism, and hybrid approaches. We evaluate these strategies on image classification…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-01 Vishnu Vardhan Baligodugula , Fathi Amsaad

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

We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that satisfies a given specification into an approximate objective…

Networking and Internet Architecture · Computer Science 2022-11-04 Luca Beurer-Kellner , Martin Vechev , Laurent Vanbever , Petar Veličković

In this work, we propose a generalized likelihood ratio method capable of training the artificial neural networks with some biological brain-like mechanisms,.e.g., (a) learning by the loss value, (b) learning via neurons with discontinuous…

Machine Learning · Computer Science 2019-07-12 Li Xiao , Yijie Peng , Jeff Hong , Zewu Ke , Shuhuai Yang

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Shuvam Chakraborty , Burak Uzkent , Kumar Ayush , Kumar Tanmay , Evan Sheehan , Stefano Ermon

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

Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…

Machine Learning · Computer Science 2019-09-10 Aidan N. Gomez , Ivan Zhang , Siddhartha Rao Kamalakara , Divyam Madaan , Kevin Swersky , Yarin Gal , Geoffrey E. Hinton

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the neural networks during the training period. In particular, we pick up a specific group of channels in each convolutional layer to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-06 Shibo Shen , Rongpeng Li , Zhifeng Zhao , Honggang Zhang , Yugeng Zhou

Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Huan Wang , Can Qin , Yulun Zhang , Yun Fu

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To…

Machine Learning · Computer Science 2022-10-28 Juan Cervino , Luana Ruiz , Alejandro Ribeiro

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

Machine Learning · Computer Science 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

The recent advent of automated neural network architecture search led to several methods that outperform state-of-the-art human-designed architectures. However, these approaches are computationally expensive, in extreme cases consuming GPU…

Machine Learning · Computer Science 2019-03-11 Martin Wistuba , Tejaswini Pedapati

Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the…

Machine Learning · Computer Science 2021-09-21 Alexander Kovalenko , Pavel Kordík , Magda Friedjungová

Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networks (ANNs). However, the training of SNN usually relies on surrogate gradients due to the…

Neural and Evolutionary Computing · Computer Science 2026-05-11 Himanshu Udupi , Xiaocong Yang , ChengXiang Zhai