English
Related papers

Related papers: Disparity Between Batches as a Signal for Early St…

200 papers

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Machine Learning · Computer Science 2022-08-23 Tingting Wu , Xiao Ding , Hao Zhang , Jinglong Gao , Li Du , Bing Qin , Ting Liu

What enables Stochastic Gradient Descent (SGD) to achieve better generalization than Gradient Descent (GD) in Neural Network training? This question has attracted much attention. In this paper, we study the distribution of the Stochastic…

Machine Learning · Computer Science 2019-10-28 Abhishek Panigrahi , Raghav Somani , Navin Goyal , Praneeth Netrapalli

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels. In this paper, we find that the test accuracy…

Machine Learning · Computer Science 2019-05-14 Pengfei Chen , Benben Liao , Guangyong Chen , Shengyu Zhang

While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift…

Machine Learning · Computer Science 2021-07-02 Wonju Lee , Seok-Yong Byun , Jooeun Kim , Minje Park , Kirill Chechil

Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve…

Machine Learning · Computer Science 2018-05-28 Dániel Varga , Adrián Csiszárik , Zsolt Zombori

Calibration is a fundamental property of a good predictive model: it requires that the model predicts correctly in proportion to its confidence. Modern neural networks, however, provide no strong guarantees on their calibration -- and can…

Machine Learning · Computer Science 2022-10-07 A. Michael Carrell , Neil Mallinar , James Lucas , Preetum Nakkiran

Recent success in deep learning has partially been driven by training increasingly overparametrized networks on ever larger datasets. It is therefore natural to ask: how much of the data is superfluous, which examples are important for…

Machine Learning · Computer Science 2023-03-29 Mansheej Paul , Surya Ganguli , Gintare Karolina Dziugaite

Neural networks are central to modern artificial intelligence, yet their training remains highly sensitive to data contamination. Standard neural classifiers are trained by minimizing the categorical cross-entropy loss, corresponding to…

Machine Learning · Statistics 2026-03-19 Suryasis Jana , Abhik Ghosh

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Machine Learning · Computer Science 2020-11-23 Hrayr Harutyunyan , Kyle Reing , Greg Ver Steeg , Aram Galstyan

Margin enlargement over training data has been an important strategy since perceptrons in machine learning for the purpose of boosting the robustness of classifiers toward a good generalization ability. Yet Breiman (1999) showed a dilemma…

Machine Learning · Computer Science 2021-01-05 Weizhi Zhu , Yifei Huang , Yuan Yao

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

Machine Learning · Computer Science 2018-01-17 Pratik Chaudhari , Stefano Soatto

Despite tremendous success of modern neural networks, they are known to be overconfident even when the model encounters inputs with unfamiliar conditions. Detecting such inputs is vital to preventing models from making naive predictions…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Jinsol Lee , Ghassan AlRegib

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an…

Machine Learning · Computer Science 2020-10-26 Sheng Liu , Jonathan Niles-Weed , Narges Razavian , Carlos Fernandez-Granda

Proving algorithm-dependent generalization error bounds for gradient-type optimization methods has attracted significant attention recently in learning theory. However, most existing trajectory-based analyses require either restrictive…

Machine Learning · Computer Science 2022-10-12 Xuanyuan Luo , Luo Bei , Jian Li

One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error. To overcome, we propose…

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Jihye Kim , Aristide Baratin , Yan Zhang , Simon Lacoste-Julien

Early stopping methods in deep learning face the challenge of balancing the volume of training and validation data, especially in the presence of label noise. Concretely, sparing more data for validation from training data would limit the…

Machine Learning · Computer Science 2025-02-12 Suqin Yuan , Lei Feng , Tongliang Liu

In this paper, we present a simple yet effective provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning. Our method is a simple modification to momentum SGD where we assign an individual…

Machine Learning · Computer Science 2023-06-09 Qi Qi , Yi Xu , Rong Jin , Wotao Yin , Tianbao Yang

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

Machine Learning · Computer Science 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…

Machine Learning · Computer Science 2021-03-02 Michael A. Hedderich , Dawei Zhu , Dietrich Klakow
‹ Prev 1 8 9 10 Next ›