English
Related papers

Related papers: The Implicit Bias of Logit Regularization

200 papers

Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (infinitesimal learning rate). Such researches, however, have…

Machine Learning · Computer Science 2020-12-17 Wei Huang , Weitao Du , Richard Yi Da Xu , Chunrui Liu

Confidence calibration is an emerging challenge in real-world decision systems based on foundations models when used for downstream vision classification tasks. Due to various reasons exposed, logit scores on the CLIP head remain large…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Behraj Khan , Tahir Syed

Several works have shown that the regularization mechanisms underlying deep neural networks' generalization performances are still poorly understood. In this paper, we hypothesize that deep neural networks are regularized through their…

Machine Learning · Computer Science 2021-03-12 Carbonnelle Simon , Christophe De Vleeschouwer

Despite the rapid development of machine learning algorithms for domain generalization (DG), there is no clear empirical evidence that the existing DG algorithms outperform the classic empirical risk minimization (ERM) across standard…

Machine Learning · Computer Science 2024-03-19 Rui Qiao , Bryan Kian Hsiang Low

This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label…

Machine Learning · Computer Science 2017-08-02 Xiudong Wang , Yuantao Gu

From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models. However, the impressive generalization performance of neural networks…

Machine Learning · Computer Science 2021-02-09 Taejong Joo , Uijung Chung

Inverse problems and regularization theory is a central theme in contemporary signal processing, where the goal is to reconstruct an unknown signal from partial indirect, and possibly noisy, measurements of it. A now standard method for…

Optimization and Control · Mathematics 2014-12-09 Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili

The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying…

Machine Learning · Computer Science 2019-06-18 Ryutaro Tanno , Ardavan Saeedi , Swami Sankaranarayanan , Daniel C. Alexander , Nathan Silberman

Multi-label text classification is a popular machine learning task where each document is assigned with multiple relevant labels. This task is challenging due to high dimensional features and correlated labels. Multi-label text classifiers…

Machine Learning · Statistics 2017-05-03 Bingyu Wang , Cheng Li , Virgil Pavlu , Javed Aslam

Gravitational lensing magnification modifies the observed spatial distribution of galaxies and can severely bias cosmological probes of large-scale structure if not accurately modelled. Standard approaches to modelling this magnification…

Regularization plays a pivotal role when facing the challenge of solving ill-posed inverse problems, where the number of observations is smaller than the ambient dimension of the object to be estimated. A line of recent work has studied…

Optimization and Control · Mathematics 2014-07-03 Samuel Vaiter , Mohammad Golbabaee , Jalal M. Fadili , Gabriel Peyré

Generalized linear model with $L_1$ and $L_2$ regularization is a widely used technique for solving classification, class probability estimation and regression problems. With the numbers of both features and examples growing rapidly in the…

Machine Learning · Statistics 2017-06-28 Ilya Trofimov , Alexander Genkin

Graph neural networks based on message-passing mechanisms have achieved advanced results in graph classification tasks. However, their generalization performance degrades when noisy labels are present in the training data. Most existing…

Machine Learning · Computer Science 2024-06-12 De Li , Xianxian Li , Zeming Gan , Qiyu Li , Bin Qu , Jinyan Wang

In large-scale supervised learning, penalized logistic regression (PLR) effectively mitigates overfitting through regularization, yet its performance critically depends on robust variable selection. This paper demonstrates that label noise…

Machine Learning · Computer Science 2026-02-16 Xiaofei Wu , Rongmei Liangse

Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., Zhao et al. (2017) show that these techniques inadvertently capture the societal bias hidden in the corpus…

Computation and Language · Computer Science 2020-05-14 Shengyu Jia , Tao Meng , Jieyu Zhao , Kai-Wei Chang

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

Machine Learning · Computer Science 2026-05-29 Hua Li

Label smoothing is a regularization technique for neural networks. Normally neural models are trained to an output distribution that is a vector with a single 1 for the correct prediction, and 0 for all other elements. Label smoothing…

Software Engineering · Computer Science 2023-03-29 Sakib Haque , Aakash Bansal , Collin McMillan

Weak lensing experiments are a powerful probe of cosmology through their measurement of the mass distribution of the universe. A challenge for this technique is to control systematic errors that occur when measuring the shapes of distant…

Cosmology and Nongalactic Astrophysics · Physics 2015-06-04 Alexandre Refregier , Tomasz Kacprzak , Adam Amara , Sarah Bridle , Barnaby Rowe

In the machine learning literature stochastic gradient descent has recently been widely discussed for its purported implicit regularization properties. Much of the theory, that attempts to clarify the role of noise in stochastic gradient…

Machine Learning · Computer Science 2022-10-21 Alberto Lanconelli , Christopher S. A. Lauria

Simplicity bias is an intriguing phenomenon prevalent in various input-output maps, characterized by a preference for simpler, more regular, or symmetric outputs. Notably, these maps typically feature high-probability outputs with simple…

Information Theory · Computer Science 2024-04-10 Boumediene Hamzi , Kamaludin Dingle