English
Related papers

Related papers: Why Does Sharpness-Aware Minimization Generalize B…

200 papers

Foundation models like the Segment Anything Model (SAM) show strong generalization, yet adapting them to medical images remains difficult due to domain shift, scarce labels, and the inability of Parameter-Efficient Fine-Tuning (PEFT) to…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Vi Vu , Thanh-Huy Nguyen , Tien-Thinh Nguyen , Ba-Thinh Lam , Hoang-Thien Nguyen , Tianyang Wang , Xingjian Li , Min Xu

This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose…

Machine Learning · Computer Science 2025-07-23 Zhihan Zeng , Yiqi Gu

Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine convergence and generalization, even with homogeneous data distributions. This work…

Machine Learning · Computer Science 2026-02-04 Zesen Wang , Mikael Johansson

Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…

Machine Learning · Computer Science 2020-02-18 Tao Lin , Sebastian U. Stich , Kumar Kshitij Patel , Martin Jaggi

In recent years, stochastic gradient descent (SGD) based techniques has become the standard tools for training neural networks. However, formal theoretical understanding of why SGD can train neural networks in practice is largely missing.…

Machine Learning · Computer Science 2017-11-03 Yuanzhi Li , Yang Yuan

The memorization problem is well-known in the field of computer vision. Liu et al. propose a technique called Early-Learning Regularization, which improves accuracy on the CIFAR datasets when label noise is present. This project replicates…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Alessio Galatolo , Alfred Nilsson , Roderick Karlemstrand , Yineng Wang

Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environments. Sparse neural networks significantly alleviate these…

Machine Learning · Computer Science 2026-03-16 Jie Ji , Gen Li , Kaiyuan Deng , Fatemeh Afghah , Xiaolong Ma

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

Pretraining optimizers are tuned to produce the strongest possible base model, on the assumption that a stronger starting point yields a stronger model after subsequent changes like post-training and quantization. This overlooks the…

Machine Learning · Computer Science 2026-05-05 Ishaan Watts , Catherine Li , Sachin Goyal , Jacob Mitchell Springer , Aditi Raghunathan

Neural networks trained with stochastic gradient descent exhibit an inductive bias towards simpler decision boundaries, typically converging to a narrow family of functions, and often fail to capture more complex features. This phenomenon…

Machine Learning · Computer Science 2024-11-08 Rahul Vashisht , P. Krishna Kumar , Harsha Vardhan Govind , Harish G. Ramaswamy

Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining.…

Machine Learning · Computer Science 2026-04-02 Yuze Wang , Yujia Tong , Xuan Liu , Junhao Dong

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bousquet and Elisseeff.…

Machine Learning · Computer Science 2016-02-09 Moritz Hardt , Benjamin Recht , Yoram Singer

In recent years, genetic programming (GP)-based evolutionary feature construction has achieved significant success. However, a primary challenge with evolutionary feature construction is its tendency to overfit the training data, resulting…

Machine Learning · Computer Science 2024-05-14 Hengzhe Zhang , Qi Chen , Bing Xue , Wolfgang Banzhaf , Mengjie Zhang

Recent advancements in learning algorithms have demonstrated that the sharpness of the loss surface is an effective measure for improving the generalization gap. Building upon this concept, Sharpness-Aware Minimization (SAM) was proposed to…

Machine Learning · Computer Science 2024-06-21 Tanapat Ratchatorn , Masayuki Tanaka

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving…

Machine Learning · Computer Science 2024-05-30 Feng Chen , Daniel Kunin , Atsushi Yamamura , Surya Ganguli

Dataset condensation aims to synthesize datasets with a few representative samples that can effectively represent the original datasets. This enables efficient training and produces models with performance close to those trained on the…

Machine Learning · Computer Science 2025-02-05 Boyan Gao , Bo Zhao , Shreyank N Gowda , Xingrun Xing , Yibo Yang , Timothy Hospedales , David A. Clifton

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi

Adaptive optimizers such as Adam (Kingma & Ba, 2015) have been central to the success of large language models. However, they often require to maintain optimizer states throughout training, which can result in memory requirements several…

Machine Learning · Computer Science 2025-02-24 Chao Ma , Wenbo Gong , Meyer Scetbon , Edward Meeds

Surrogate gradients are a standard tool for training spiking neural networks (SNNs), but conventional hard forward or surrogate backward training couples a nonsmooth forward model with a biased gradient estimator. We study sharpness aware…

Neural and Evolutionary Computing · Computer Science 2026-03-20 Maximilian Nicholson

Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a prevalent yet under-explored phenomenon in graph generalization,…

Machine Learning · Computer Science 2026-02-10 Yang Qiu , Yixiong Zou , Jun Wang
‹ Prev 1 8 9 10 Next ›