English
Related papers

Related papers: Stabilizing Sharpness-aware Minimization Through A…

200 papers

Despite superior training outcomes, adaptive optimization methods such as Adam, Adagrad or RMSprop have been found to generalize poorly compared to Stochastic gradient descent (SGD). These methods tend to perform well in the initial portion…

Machine Learning · Computer Science 2017-12-21 Nitish Shirish Keskar , Richard Socher

Multi-task learning (MTL) enables a joint model to capture commonalities across multiple tasks, reducing computation costs and improving data efficiency. However, a major challenge in MTL optimization is task conflicts, where the task…

Machine Learning · Computer Science 2025-07-17 Hao Ban , Gokul Ram Subramani , Kaiyi Ji

Gradient descent algorithm is the most utilized method when optimizing machine learning issues. However, there exists many local minimums and saddle points in the loss function, especially for high dimensional non-convex optimization…

Machine Learning · Computer Science 2021-07-19 Zhicheng Cai

Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as…

Machine Learning · Computer Science 2025-07-08 Chenyang Ren , Yifan Jia , Huanyi Xie , Zhaobin Xu , Tianxing Wei , Liangyu Wang , Lijie Hu , Di Wang

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

Modern machine learning solutions require extensive data collection where labeling remains costly. To reduce this burden, open set active learning approaches aim to select informative samples from a large pool of unlabeled data that…

Machine Learning · Computer Science 2025-10-27 Young In Kim , Andrea Agiollo , Rajiv Khanna

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN weights during…

Machine Learning · Computer Science 2023-03-22 Gonçalo Mordido , Sébastien Henwood , Sarath Chandar , François Leduc-Primeau

SGD (Stochastic Gradient Descent) is a popular algorithm for large scale optimization problems due to its low iterative cost. However, SGD can not achieve linear convergence rate as FGD (Full Gradient Descent) because of the inherent…

Machine Learning · Computer Science 2017-12-05 Aixiang Chen , Bingchuan Chen , Xiaolong Chai , Rui Bian , Hengguang Li

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

Sharpness-Aware Minimization (SAM) is most known for achieving state-of the-art performances on natural image and language tasks. However, its most pronounced improvements (of tens of percent) is rather in the presence of label noise.…

Machine Learning · Computer Science 2024-05-07 Christina Baek , Zico Kolter , Aditi Raghunathan

Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distribution across these sparsely connected learning agents can be…

Machine Learning · Computer Science 2025-02-27 Sakshi Choudhary , Sai Aparna Aketi , Kaushik Roy

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

The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by…

Optimization and Control · Mathematics 2025-11-21 Fabio Nobile , Matteo Raviola , Nathan Schaeffer

In this paper, we study the implicit regularization of stochastic gradient descent (SGD) through the lens of {\em dynamical stability} (Wu et al., 2018). We start by revising existing stability analyses of SGD, showing how the Frobenius…

Machine Learning · Statistics 2023-06-02 Lei Wu , Weijie J. Su

Stochastic approximation (SA) is a key method used in statistical learning. Recently, its non-asymptotic convergence analysis has been considered in many papers. However, most of the prior analyses are made under restrictive assumptions…

Machine Learning · Statistics 2019-06-18 Belhal Karimi , Blazej Miasojedow , Eric Moulines , Hoi-To Wai

We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…

Machine Learning · Computer Science 2020-03-04 Achraf Bahamou , Donald Goldfarb

In an effort to improve generalization in deep learning and automate the process of learning rate scheduling, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers. Our method dynamically…

Machine Learning · Computer Science 2023-07-04 Xubo Yue , Maher Nouiehed , Raed Al Kontar

The stochastic gradient descent (SGD) algorithm has achieved remarkable success in training deep learning models. However, it has several limitations, including susceptibility to vanishing gradients, sensitivity to input data, and a lack of…

Machine Learning · Computer Science 2025-03-14 Chengcheng Yan , Jiawei Xu , Qingsong Wang , Zheng Peng

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