English
Related papers

Related papers: The Implicit Bias of Logit Regularization

200 papers

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Chaowei Fang , Lechao Cheng , Huiyan Qi , Dingwen Zhang

In machine learning, classifiers are typically susceptible to noise in the training data. In this work, we aim at reducing intra-class noise with the help of graph filtering to improve the classification performance. Considered graphs are…

Machine Learning · Statistics 2021-01-26 Mounia Hamidouche , Carlos Lassance , Yuqing Hu , Lucas Drumetz , Bastien Pasdeloup , Vincent Gripon

An open scientific challenge is how to classify events with reliable measures of uncertainty, when we have a mechanistic model of the data-generating process but the distribution over both labels and latent nuisance parameters is different…

Machine Learning · Statistics 2024-07-02 Luca Masserano , Alex Shen , Michele Doro , Tommaso Dorigo , Rafael Izbicki , Ann B. Lee

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the role of the label noise in the training dynamics of a…

Machine Learning · Statistics 2022-06-22 Loucas Pillaud-Vivien , Julien Reygner , Nicolas Flammarion

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from…

Sound · Computer Science 2019-10-29 Eduardo Fonseca , Frederic Font , Xavier Serra

Consistency regularization is a commonly-used technique for semi-supervised and self-supervised learning. It is an auxiliary objective function that encourages the prediction of the network to be similar in the vicinity of the observed…

Machine Learning · Computer Science 2021-10-05 Erik Englesson , Hossein Azizpour

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have been studied…

Machine Learning · Computer Science 2025-08-25 Tom Jacobs , Chao Zhou , Rebekka Burkholz

We systematically explore regularizing neural networks by penalizing low entropy output distributions. We show that penalizing low entropy output distributions, which has been shown to improve exploration in reinforcement learning, acts as…

Neural and Evolutionary Computing · Computer Science 2017-01-24 Gabriel Pereyra , George Tucker , Jan Chorowski , Łukasz Kaiser , Geoffrey Hinton

The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal…

Machine Learning · Computer Science 2021-11-09 Ganesh Ramachandra Kini , Orestis Paraskevas , Samet Oymak , Christos Thrampoulidis

We study Langevin dynamics with noise projected onto the directions orthogonal to an isometric group action. This mathematical model is introduced to shed new light on the effects of symmetry on stochastic gradient descent for…

Probability · Mathematics 2026-02-13 Govind Menon , Austin J. Stromme , Adrien Vacher

Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one particular way of random perturbation, which corresponds to…

Machine Learning · Computer Science 2021-02-16 Oussama Dhifallah , Yue M. Lu

Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce…

Machine Learning · Computer Science 2026-02-02 Jaeseung Heo , Moonjeong Park , Dongwoo Kim

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they…

Machine Learning · Computer Science 2022-11-30 Jongwoo Ko , Bongsoo Yi , Se-Young Yun

Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this…

Machine Learning · Computer Science 2025-01-28 Max Staats , Matthias Thamm , Bernd Rosenow

This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label…

Machine Learning · Statistics 2021-06-14 Shuhei M. Yoshida , Takashi Takenouchi , Masashi Sugiyama

Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent…

Machine Learning · Computer Science 2022-06-28 Yingyi Chen , Shell Xu Hu , Xi Shen , Chunrong Ai , Johan A. K. Suykens

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Beier Zhu , Kaihua Tang , Qianru Sun , Hanwang Zhang

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