English
Related papers

Related papers: Enhancing Generalization via Sharpness-Aware Traje…

200 papers

Graph distillation has emerged as a solution for reducing large graph datasets to smaller, more manageable, and informative ones. Existing methods primarily target node classification, involve computationally intensive processes, and fail…

Machine Learning · Computer Science 2024-09-02 Arash Rasti-Meymandi , Ahmad Sajedi , Zhaopan Xu , Konstantinos N. Plataniotis

Recent innovations in Transformer-based large language models have significantly advanced the field of general-purpose neural language understanding and generation. With billions of trainable parameters, deployment of these large models…

Hardware Architecture · Computer Science 2024-10-11 Haocheng Xu , Faraz Tahmasebi , Ye Qiao , Hongzheng Tian , Hyoukjun Kwon , Sitao Huang

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…

Machine Learning · Computer Science 2025-10-09 Dung Hoang-Anh , Cuong Pham Trung Le , Jianfei Cai , Thanh-Toan Do

Dataset condensation is a newborn technique that generates a small dataset that can be used in training deep neural networks to lower training costs. The objective of dataset condensation is to ensure that the model trained with the…

Machine Learning · Computer Science 2024-10-24 Jianrong Ding , Zhanyu Liu , Guanjie Zheng , Haiming Jin , Linghe Kong

Generalization of neural networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations, ensembling and model averaging. In this work, we first…

Machine Learning · Computer Science 2023-06-13 Samyak Jain , Sravanti Addepalli , Pawan Sahu , Priyam Dey , R. Venkatesh Babu

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires \emph{sequentially} computing two gradients, effectively doubling the per-iteration cost compared to base…

Machine Learning · Computer Science 2024-10-15 Wanyun Xie , Thomas Pethick , Volkan Cevher

Sharpness-aware minimization (SAM) has well-documented merits in enhancing generalization of deep neural network models. Accounting for sharpness in the loss function geometry, where neighborhoods of `flat minima' heighten generalization…

Machine Learning · Computer Science 2025-09-03 Bingcong Li , Yilang Zhang , Georgios B. Giannakis

Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Qian Zeng , Jie Song , Yuanyu Wan , Huiqiong Wang , Mingli Song

Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss landscape near the local minima to which they converge. This suggests that qualitative and quantitative…

Machine Learning · Computer Science 2022-01-28 Stefan Horoi , Jessie Huang , Bastian Rieck , Guillaume Lajoie , Guy Wolf , Smita Krishnaswamy

Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones. This is essential for addressing the challenges of data storage and training costs. Prevalent…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Yanqing Liu , Jianyang Gu , Kai Wang , Zheng Zhu , Kaipeng Zhang , Wei Jiang , Yang You

Sharpness-aware minimization (SAM) encourages flat minima by perturbing parameters along directions of high loss curvature, but treats all parameter directions uniformly, ignoring the underlying loss geometry. We introduce LLQR+SAM, which…

Machine Learning · Computer Science 2026-05-18 Simon Dufort-Labbé , Mehrab Hamidi , Razvan Pascanu , Ioannis Mitliagkas , Damien Scieur , Aristide Baratin

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ruixi Wu , Shaobo Wang , Jiahuan Chen , Zhiyuan Liu , Yicun Yang , Zhaorun Chen , Zekai Li , Kaixin Li , Xinming Wang , Hongzhu Yi , Kai Wang , Linfeng Zhang

In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resulted global model. Prevalent federated approaches incorporate…

Machine Learning · Computer Science 2024-05-30 Ziqing Fan , Shengchao Hu , Jiangchao Yao , Gang Niu , Ya Zhang , Masashi Sugiyama , Yanfeng Wang

Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chenru Wang , Yunyi Chen , Zijun Yang , Joey Tianyi Zhou , Chi Zhang

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Tao Hu , Lichao Huang , Xianming Liu , Han Shen

Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains,…

Machine Learning · Computer Science 2024-03-14 Anna Bair , Hongxu Yin , Maying Shen , Pavlo Molchanov , Jose Alvarez

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relatively high memory…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Chaim Baskin , Brian Chmiel , Evgenii Zheltonozhskii , Ron Banner , Alex M. Bronstein , Avi Mendelson

Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model…

Computation and Language · Computer Science 2022-10-12 Qihuang Zhong , Liang Ding , Li Shen , Peng Mi , Juhua Liu , Bo Du , Dacheng Tao

Dataset distillation extracts a small set of synthetic training samples from a large dataset with the goal of achieving competitive performance on test data when trained on this sample. In this work, we tackle dataset distillation at its…

Machine Learning · Computer Science 2023-11-14 Yunzhen Feng , Ramakrishna Vedantam , Julia Kempe

Increasing and massive volumes of trajectory data are being accumulated that may serve a variety of applications, such as mining popular routes or identifying ridesharing candidates. As storing and querying massive trajectory data is…

Databases · Computer Science 2023-12-14 Zheng Wang , Cheng Long , Gao Cong , Christian S. Jensen