English
Related papers

Related papers: A Study of Gradient Variance in Deep Learning

200 papers

Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…

Machine Learning · Statistics 2015-11-24 Arvind Neelakantan , Luke Vilnis , Quoc V. Le , Ilya Sutskever , Lukasz Kaiser , Karol Kurach , James Martens

Gradient regularization, as described in \citet{barrett2021implicit}, is a highly effective technique for promoting flat minima during gradient descent. Empirical evidence suggests that this regularization technique can significantly…

Machine Learning · Statistics 2023-04-03 Xuran Meng , Yuan Cao , Difan Zou

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

Machine Learning · Computer Science 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…

Machine Learning · Computer Science 2022-08-02 Zixuan Jiang , Jiaqi Gu , Mingjie Liu , David Z. Pan

Training large machine learning models requires a distributed computing approach, with communication of the model updates being the bottleneck. For this reason, several methods based on the compression (e.g., sparsification and/or…

Machine Learning · Computer Science 2023-12-29 Konstantin Mishchenko , Eduard Gorbunov , Martin Takáč , Peter Richtárik

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

Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…

Machine Learning · Computer Science 2019-12-06 Yi Sun , Yan Tian , Yiping Xu , Jianxiang Li

Sampling methods (e.g., node-wise, layer-wise, or subgraph) has become an indispensable strategy to speed up training large-scale Graph Neural Networks (GNNs). However, existing sampling methods are mostly based on the graph structural…

Machine Learning · Computer Science 2021-09-07 Weilin Cong , Rana Forsati , Mahmut Kandemir , Mehrdad Mahdavi

We study the discrete dynamics of mini-batch gradient descent with random reshuffling for least squares regression. We show that the training and generalization errors depend on a sample cross-covariance matrix $Z$ between the original…

Machine Learning · Statistics 2025-02-05 Jackie Lok , Rishi Sonthalia , Elizaveta Rebrova

In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. When the aim is to make predictions on distributions different from those seen at…

Machine Learning · Computer Science 2021-11-04 Lucas Mansilla , Rodrigo Echeveste , Diego H. Milone , Enzo Ferrante

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Machine Learning · Computer Science 2025-12-05 Dravyansh Sharma

Informative gradients are often lost in large batch updates. We propose a robust mechanism to reinforce the sparse components within a random batch of data points. A finite queue of online gradients is used to determine their expected…

Machine Learning · Computer Science 2024-04-29 Irfan Mohammad Al Hasib

Vanishing (and exploding) gradients effect is a common problem for recurrent neural networks with nonlinear activation functions which use backpropagation method for calculation of derivatives. Deep feedforward neural networks with many…

Neural and Evolutionary Computing · Computer Science 2017-02-15 Artem Chernodub , Dimitri Nowicki

Variational quantum algorithms are expected to demonstrate the advantage of quantum computing on near-term noisy quantum computers. However, training such variational quantum algorithms suffers from gradient vanishing as the size of the…

Quantum Physics · Physics 2021-11-29 Anbang Wu , Gushu Li , Yufei Ding , Yuan Xie

LLM training is resource-intensive. Quantized training improves computational and memory efficiency but introduces quantization noise, which can hinder convergence and degrade model accuracy. Stochastic Rounding (SR) has emerged as a…

Machine Learning · Computer Science 2025-11-04 Taowen Liu , Marta Andronic , Deniz Gündüz , George A. Constantinides

In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization. The technique essentially contains two consecutive steps in each iteration: 1) computing and normalizing each block…

Machine Learning · Computer Science 2018-04-24 Adams Wei Yu , Lei Huang , Qihang Lin , Ruslan Salakhutdinov , Jaime Carbonell

Data imbalance is a common problem in machine learning that can have a critical effect on the performance of a model. Various solutions exist but their impact on the convergence of the learning dynamics is not understood. Here, we elucidate…

Machine Learning · Statistics 2024-02-20 Emanuele Francazi , Marco Baity-Jesi , Aurelien Lucchi

Many learning tasks in machine learning can be viewed as taking a gradient step towards minimizing the average loss of a batch of examples in each training iteration. When noise is prevalent in the data, this uniform treatment of examples…

Machine Learning · Computer Science 2021-04-06 Negin Majidi , Ehsan Amid , Hossein Talebi , Manfred K. Warmuth

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

Machine Learning · Computer Science 2021-01-08 Kaustubh Yadav

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy