ICML 2024 "sharpness-aware minimization" Papers
10 papers found
A Universal Class of Sharpness-Aware Minimization Algorithms
Behrooz Tahmasebi, Ashkan Soleymani, Dara Bahri et al.
ICML 2024poster
Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM Dynamics
Ankit Vani, Frederick Tung, Gabriel Oliveira et al.
ICML 2024poster
How to Escape Sharp Minima with Random Perturbations
Kwangjun Ahn, Ali Jadbabaie, Suvrit Sra
ICML 2024poster
Improving SAM Requires Rethinking its Optimization Formulation
Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos et al.
ICML 2024poster
Improving Sharpness-Aware Minimization by Lookahead
Runsheng Yu, Youzhi Zhang, James Kwok
ICML 2024poster
Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Ziqing Fan, Shengchao Hu, Jiangchao Yao et al.
ICML 2024spotlight
Lookbehind-SAM: k steps back, 1 step forward
Gonçalo Mordido, Pranshu Malviya, Aristide Baratin et al.
ICML 2024poster
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
Yihao Zhang, Hangzhou He, Jingyu Zhu et al.
ICML 2024poster
Rethinking the Flat Minima Searching in Federated Learning
Taehwan Lee, Sung Whan Yoon
ICML 2024poster
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention
Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov et al.
ICML 2024poster