Results 261 to 270 of about 836,502 (333)

Congrès SHARP 2015 / SHARP 2015 Conference

, 2014
openaire   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

FedGAMMA: Federated Learning With Global Sharpness-Aware Minimization

IEEE Transactions on Neural Networks and Learning Systems, 2023
Federated learning (FL) is a promising framework for privacy-preserving and distributed training with decentralized clients. However, there exists a large divergence between the collected local updates and the expected global update, which is known as ...
Rong Dai, Xun Yang, Yan Sun, Li Shen, Xinmei Tian, Meng Wang, Yongdong Zhang   +6 more
semanticscholar   +1 more source

Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition

Computer Vision and Pattern Recognition, 2023
It's widely acknowledged that deep learning models with flatter minima in its loss landscape tend to generalize better. However, such property is under-explored in deep long-tailed recognition (DLTR), a practical problem where the model is required to ...
Zhipeng Zhou, Lanqing Li, P. Zhao, P. Heng, Wei Gong   +4 more
semanticscholar   +1 more source

Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization

arXiv.org
Sharpness-Aware Minimization (SAM) has attracted significant attention for its effectiveness in improving generalization across various tasks. However, its underlying principles remain poorly understood.
Haocheng Luo, Tuan Truong, Tung Pham, Mehrtash Harandi, Dinh Q. Phung, Trung Le   +5 more
semanticscholar   +1 more source

Random Sharpness-Aware Minimization

Neural Information Processing Systems, 2022
Currently, Sharpness-Aware Minimization (SAM) is proposed to seek the parameters that lie in a flat region to improve the generalization when training neural networks.
Y. Liu, Siqi Mai, Minhao Cheng, Xiangning Chen, Cho-Jui Hsieh, Yang You   +5 more
semanticscholar   +1 more source

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

International Conference on Machine Learning
Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of ...
Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He   +6 more
semanticscholar   +1 more source

SHARP

Proceedings of the 4th ACM international symposium on Mobile ad hoc networking & computing - MobiHoc '03, 2003
A central challenge in ad hoc networks is the design of routing protocols that can adapt their behavior to frequent and rapid changes in the network. The performance of proactive and reactive routing protocols varies with network characteristics, and one protocol may outperform the other in different network conditions.
Venugopalan Ramasubramanian, Zygmunt J. Haas, Emin Gün Sirer   +2 more
openaire   +2 more sources