English
Related papers

Related papers: The Implicit Bias of Logit Regularization

200 papers

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demonstrate that training…

Machine Learning · Computer Science 2021-12-07 Alex Damian , Tengyu Ma , Jason D. Lee

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…

Machine Learning · Statistics 2026-05-08 Joseph H. Rudoler , Kevin Tan , Giles Hooker , Konrad P. Kording

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often…

Machine Learning · Computer Science 2019-10-28 Ali Shafahi , Amin Ghiasi , Furong Huang , Tom Goldstein

Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ``Hard'' one-hot labels are ``smoothed'' by uniformly distributing probability…

Machine Learning · Computer Science 2025-02-21 Guoxuan Xia , Olivier Laurent , Gianni Franchi , Christos-Savvas Bouganis

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

Label smoothing (LS) is an arising learning paradigm that uses the positively weighted average of both the hard training labels and uniformly distributed soft labels. It was shown that LS serves as a regularizer for training data with hard…

Machine Learning · Computer Science 2022-06-28 Jiaheng Wei , Hangyu Liu , Tongliang Liu , Gang Niu , Masashi Sugiyama , Yang Liu

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Machine Learning · Computer Science 2023-06-02 Dan Zhao

Regularization is an effective way to promote the generalization performance of machine learning models. In this paper, we focus on label smoothing, a form of output distribution regularization that prevents overfitting of a neural network…

Machine Learning · Computer Science 2020-07-07 Weizhi Li , Gautam Dasarathy , Visar Berisha

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the…

Machine Learning · Computer Science 2020-12-23 Assaf Dauber , Meir Feder , Tomer Koren , Roi Livni

The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels…

Machine Learning · Computer Science 2020-06-12 Rafael Müller , Simon Kornblith , Geoffrey Hinton

We investigate the mechanisms of self-distillation in multi-class classification, particularly in the context of linear probing with fixed feature extractors where traditional feature learning explanations do not apply. Our theoretical…

Machine Learning · Computer Science 2025-02-20 Hyeonsu Jeong , Hye Won Chung

Overparameterized models may have many interpolating solutions; implicit regularization refers to the hidden preference of a particular optimization method towards a certain interpolating solution among the many. A by now established line…

Machine Learning · Computer Science 2024-09-18 Hung-Hsu Chou , Holger Rauhut , Rachel Ward

Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes…

Machine Learning · Computer Science 2021-07-13 Aditya Krishna Menon , Sadeep Jayasumana , Ankit Singh Rawat , Himanshu Jain , Andreas Veit , Sanjiv Kumar

Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In…

Machine Learning · Computer Science 2020-03-06 Michal Lukasik , Srinadh Bhojanapalli , Aditya Krishna Menon , Sanjiv Kumar

In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been shown to be not robust to noisy labels due to its…

Machine Learning · Computer Science 2023-06-14 Hongxin Wei , Huiping Zhuang , Renchunzi Xie , Lei Feng , Gang Niu , Bo An , Yixuan Li

We consider a high-dimensional mixture of two Gaussians in the noisy regime where even an oracle knowing the centers of the clusters misclassifies a small but finite fraction of the points. We provide a rigorous analysis of the…

Machine Learning · Statistics 2021-03-22 Francesca Mignacco , Florent Krzakala , Yue M. Lu , Lenka Zdeborová

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Wei Hu , Yuping Luo

While the Implicit Bias(or Implicit Regularization) of standard loss functions has been studied, the optimization geometry induced by discriminative metric-learning objectives remains largely unexplored.To the best of our knowledge, this…

Machine Learning · Computer Science 2026-04-13 Jiawen Li

Label noise presents a real challenge for supervised learning algorithms. Consequently, mitigating label noise has attracted immense research in recent years. Noise robust losses is one of the more promising approaches for dealing with…

Machine Learning · Computer Science 2021-04-27 Neta Shoham , Tomer Avidor , Nadav Israel

Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a strong implicit regularization by replacing the target…

Machine Learning · Computer Science 2022-05-04 Kensuke Nakamura , Bong-Soo Sohn , Kyoung-Jae Won , Byung-Woo Hong
‹ Prev 1 2 3 10 Next ›