English
Related papers

Related papers: Does SGD Seek Flatness or Sharpness? An Exactly So…

200 papers

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

Machine Learning · Computer Science 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

Stochastic gradient descent (SGD) is one of the most popular algorithms in modern machine learning. The noise encountered in these applications is different from that in many theoretical analyses of stochastic gradient algorithms. In this…

Machine Learning · Statistics 2021-09-16 Stephan Wojtowytsch

This paper proposes a theoretical framework to evaluate and compare the performance of stochastic gradient algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments. Previous works have…

Machine Learning · Computer Science 2025-07-03 Ying Cao , Zhaoxian Wu , Kun Yuan , Ali H. Sayed

Sharpness-Aware Minimization (SAM) is a recent optimization framework aiming to improve the deep neural network generalization, through obtaining flatter (i.e. less sharp) solutions. As SAM has been numerically successful, recent papers…

Machine Learning · Statistics 2023-05-22 Kayhan Behdin , Rahul Mazumder

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have…

Machine Learning · Computer Science 2021-10-12 Danruo Deng , Guangyong Chen , Jianye Hao , Qiong Wang , Pheng-Ann Heng

Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this problem. Some of these methods achieved considerable performance…

Machine Learning · Computer Science 2021-07-14 Zhongzhan Huang , Mingfu Liang , Senwei Liang , Wei He

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However,…

Machine Learning · Computer Science 2026-01-13 Yanan Chen , Tieliang Gong , Yunjiao Zhang , Wen Wen

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing…

Machine Learning · Computer Science 2021-11-30 Pan Zhou , Jiashi Feng , Chao Ma , Caiming Xiong , Steven Hoi , Weinan E

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

Machine Learning · Statistics 2022-05-13 Amanda Olmin , Fredrik Lindsten

Stochastic Gradient Descent (SGD) has become a cornerstone of neural network optimization due to its computational efficiency and generalization capabilities. However, the gradient noise introduced by SGD is often assumed to be uncorrelated…

Machine Learning · Computer Science 2025-12-23 Marcel Kühn , Bernd Rosenow

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

Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, effectively the scientific models may be ignored in…

Machine Learning · Computer Science 2026-02-09 Naoya Takeishi

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…

Machine Learning · Computer Science 2023-06-12 Jinseong Park , Hoki Kim , Yujin Choi , Jaewook Lee

We study the SAM (Sharpness-Aware Minimization) optimizer which has recently attracted a lot of interest due to its increased performance over more classical variants of stochastic gradient descent. Our main contribution is the derivation…

Machine Learning · Computer Science 2023-06-06 Enea Monzio Compagnoni , Luca Biggio , Antonio Orvieto , Frank Norbert Proske , Hans Kersting , Aurelien Lucchi

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli

Deep neural network training often exhibits highly anisotropic loss geometry, where a few sharp dominant Hessian directions coexist with a large flatter bulk. Gradients tend to align disproportionately with these dominant directions,…

Machine Learning · Computer Science 2026-05-28 Tolga Dimlioglu , Kristi Topollai , Anna Choromanska

It is arguably believed that flatter minima can generalize better. However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the integral of loss over a $\delta$ ball of parameters around…

Machine Learning · Computer Science 2021-01-11 Mingyang Yi , Huishuai Zhang , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

Stochastic Gradient Descent (SGD) is a central tool in machine learning. We prove that SGD converges to zero loss, even with a fixed (non-vanishing) learning rate - in the special case of homogeneous linear classifiers with smooth monotone…

Machine Learning · Statistics 2022-04-19 Mor Shpigel Nacson , Nathan Srebro , Daniel Soudry

Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is vital for fostering trust and comprehension in these models.…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Amira Guesmi , Nishant Suresh Aswani , Muhammad Shafique

We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise,…

Machine Learning · Computer Science 2020-07-09 Amartya Sanyal , Puneet K Dokania , Varun Kanade , Philip H. S. Torr