English
Related papers

Related papers: The Two Regimes of Deep Network Training

200 papers

Deep Neural Networks (DNNs) rely on inherent fluctuations in their internal parameters (weights and biases) to effectively navigate the complex optimization landscape and achieve robust performance. While these fluctuations are recognized…

Machine Learning · Computer Science 2025-11-14 Darsh Pareek , Umesh Kumar , Ruthu Rao , Ravi Janjam

Deep learning techniques are increasingly applied to scientific problems, where the precision of networks is crucial. Despite being deemed as universal function approximators, neural networks, in practice, struggle to reduce the prediction…

Machine Learning · Computer Science 2023-07-19 Yongji Wang , Ching-Yao Lai

Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world…

Machine Learning · Computer Science 2023-09-19 Hongpeng Jin , Wenqi Wei , Xuyu Wang , Wenbin Zhang , Yanzhao Wu

Machine translation systems based on deep neural networks are expensive to train. Curriculum learning aims to address this issue by choosing the order in which samples are presented during training to help train better models faster. We…

Computation and Language · Computer Science 2018-11-05 Xuan Zhang , Gaurav Kumar , Huda Khayrallah , Kenton Murray , Jeremy Gwinnup , Marianna J Martindale , Paul McNamee , Kevin Duh , Marine Carpuat

Deep Reinforcement Learning (DRL) methods often rely on the meticulous tuning of hyperparameters to successfully resolve problems. One of the most influential parameters in optimization procedures based on stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-08-05 Ralf Gulde , Marc Tuscher , Akos Csiszar , Oliver Riedel , Alexander Verl

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Machine Learning · Statistics 2022-07-05 Elvis Dohmatob , Alberto Bietti

We study two factors in neural network training: data parallelism and sparsity; here, data parallelism means processing training data in parallel using distributed systems (or equivalently increasing batch size), so that training can be…

Machine Learning · Computer Science 2021-04-05 Namhoon Lee , Thalaiyasingam Ajanthan , Philip H. S. Torr , Martin Jaggi

The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this white paper, we addressed the challenge of efficiently…

Machine Learning · Computer Science 2024-04-29 Raphael Ruschel , A. S. M. Iftekhar , B. S. Manjunath , Suya You

Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two consecutive phases…

Machine Learning · Computer Science 2017-10-11 Nanyang Ye , Zhanxing Zhu , Rafal K. Mantiuk

One of the generally accepted views of modern deep learning is that increasing the number of parameters usually leads to better quality. The two easiest ways to increase the number of parameters is to increase the size of the network, e.g.…

Machine Learning · Computer Science 2020-05-18 Nadezhda Chirkova , Ekaterina Lobacheva , Dmitry Vetrov

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

Despite exceptional achievements, training neural networks remains computationally expensive and is often plagued by instabilities that can degrade convergence. While learning rate schedules can help mitigate these issues, finding optimal…

Machine Learning · Computer Science 2026-03-30 Benoit Dherin , Benny Avelin , Anders Karlsson , Hanna Mazzawi , Javier Gonzalvo , Michael Munn

Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty…

Machine Learning · Computer Science 2022-05-30 Neeraj Varshney , Swaroop Mishra , Chitta Baral

This paper studies practical limitations of learning methods for resource management in non-stationary radio environment. We propose two learning models carefully designed to support rate maximization objective under user mobility. We study…

Signal Processing · Electrical Eng. & Systems 2020-05-07 Suren Sritharan , Harshana Weligampola , Haris Gacanin

Recent research has shown the existence of significant redundancy in large Transformer models. One can prune the redundant parameters without significantly sacrificing the generalization performance. However, we question whether the…

Computation and Language · Computer Science 2022-02-15 Chen Liang , Haoming Jiang , Simiao Zuo , Pengcheng He , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , Tuo Zhao

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions,…

Machine Learning · Computer Science 2023-12-06 Ravid Shwartz-Ziv , Micah Goldblum , Yucen Lily Li , C. Bayan Bruss , Andrew Gordon Wilson

Understanding the learning dynamics of neural networks is one of the key issues for the improvement of optimization algorithms as well as for the theoretical comprehension of why deep neural nets work so well today. In this paper, we…

Machine Learning · Statistics 2021-03-18 Zhenyu Liao , Romain Couillet

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce…

Machine Learning · Statistics 2018-06-12 Lingjiao Chen , Hongyi Wang , Jinman Zhao , Dimitris Papailiopoulos , Paraschos Koutris

The current deep learning model is of a single-grade, that is, it learns a deep neural network by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to…

Machine Learning · Computer Science 2023-02-02 Yuesheng Xu

This paper presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…

Neural and Evolutionary Computing · Computer Science 2016-01-05 Conrado S. Miranda , Fernando J. Von Zuben
‹ Prev 1 4 5 6 7 8 10 Next ›