English
Related papers

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

200 papers

We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a suitable choice of semimetric, we establish a contraction in…

Machine Learning · Statistics 2023-11-02 Jung Eun Huh , Patrick Rebeschini

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

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

Many audio processing tasks require perceptual assessment. The ``gold standard`` of obtaining human judgments is time-consuming, expensive, and cannot be used as an optimization criterion. On the other hand, automated metrics are efficient…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Pranay Manocha , Adam Finkelstein , Richard Zhang , Nicholas J. Bryan , Gautham J. Mysore , Zeyu Jin

Errors in labels obtained via human annotation adversely affect a model's performance. Existing approaches propose ways to mitigate the effect of label error on a model's downstream accuracy, yet little is known about its impact on a…

Machine Learning · Computer Science 2023-10-05 Julius Adebayo , Melissa Hall , Bowen Yu , Bobbie Chern

A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier could be learned from similarity-labeled pairwise data by meta…

Machine Learning · Computer Science 2020-02-18 Songhua Wu , Xiaobo Xia , Tongliang Liu , Bo Han , Mingming Gong , Nannan Wang , Haifeng Liu , Gang Niu

Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples, with evaluation largely driven by held-out performance and perceived sample quality. In…

Machine Learning · Computer Science 2026-03-05 Jerome Garnier-Brun , Luca Biggio , Davide Beltrame , Marc Mézard , Luca Saglietti

Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…

Machine Learning · Computer Science 2022-10-04 Daniel Shwartz , Uri Stern , Daphna Weinshall

Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this, some methods were proposed to automatically split clean…

Machine Learning · Computer Science 2022-12-20 Daehwan Kim , Kwangrok Ryoo , Hansang Cho , Seungryong Kim

Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early…

Computer Vision and Pattern Recognition · Computer Science 2022-12-08 Huaxi Huang , Hui Kang , Sheng Liu , Olivier Salvado , Thierry Rakotoarivelo , Dadong Wang , Tongliang Liu

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

Machine Learning · Computer Science 2020-02-28 Xiangrui Li , Deng Pan , Xin Li , Dongxiao Zhu

Recognizing and telling similar objects apart is even hard for human beings. In this paper, we show that there is a phenomenon of class interference with all deep neural networks. Class interference represents the learning difficulty in…

Machine Learning · Computer Science 2022-11-04 Dongcui Diao , Hengshuai Yao , Bei Jiang

The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the training of deep networks for classification. We will show that…

Machine Learning · Computer Science 2020-04-14 Andrzej Banburski , Qianli Liao , Brando Miranda , Lorenzo Rosasco , Fernanda De La Torre , Jack Hidary , Tomaso Poggio

Deep neural networks (DNNs) have achieved remarkable empirical success, yet their training dynamics remain understood mainly from optimization rather than statistical principles. Here we develop a statistical framework for DNN training in…

Machine Learning · Statistics 2026-05-28 Minhao Yao , Ruoyu Wang , Xihong Lin , Lin Liu , Zhonghua Liu

Stochastic gradient descent plays a fundamental role in nearly all applications of deep learning. However its ability to converge to a global minimum remains shrouded in mystery. In this paper we propose to study the behavior of the loss…

Machine Learning · Computer Science 2023-02-02 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Nolan Miller

Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test loss follows a decreasing-increasing-decreasing pattern (or…

Machine Learning · Computer Science 2024-05-09 Yihao Xue , Kyle Whitecross , Baharan Mirzasoleiman

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

In machine learning, the performance of a classifier depends on both the classifier model and the dataset. For a specific neural network classifier, the training process varies with the training set used; some training data make training…

Machine Learning · Computer Science 2020-06-01 Shuyue Guan , Murray Loew , Hanseok Ko

In this paper, we study the implicit bias of gradient descent for sparse regression. We extend results on regression with quadratic parametrization, which amounts to depth-2 diagonal linear networks, to more general depth-N networks, under…

Machine Learning · Statistics 2021-10-28 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

Machine Learning · Computer Science 2021-10-12 Yi-Lun Wu , Hong-Han Shuai , Zhi-Rui Tam , Hong-Yu Chiu