conftrace_

sharpness-aware minimization

81 papers

Explore in graph

Also known as

SAM

Co-occurring keywords

neural network optimization (1293) loss landscape (149) flat minima (50) model generalization (190) gradient descent (1144) stochastic gradient descent (1091) neural network (6616) generalization bound (652) adversarial perturbation (384) flat minimum (15)

Papers

Beyond Sharpness: The Role of Nonuniformity in Generalization AAAI 2026
Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Models AAAI 2026
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD AAAI 2026
TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation ACL 2026
Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization (Student Abstract) AAAI 2026
Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026
Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections MIDL 2026
Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better Stability AAAI 2026
Efficiently Seeking Flat Minima for Better Generalization in Fine-Tuning Large Language Models and Beyond AAAI 2026
Stabilizing Sharpness-Aware Minimization Through A Simple Renormalization Strategy JMLR 2025
SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data WACV 2025
Sharpness-aware Zeroth-order Optimization for Graph Transformers IJCAI 2025
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation ICCV 2025
Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization AAAI 2025
Interactive Multimodal Learning via Flat Gradient Modification IJCAI 2025
Balanced Sharpness-Aware Minimization for Imbalanced Regression ICCV 2025
Flexible Sharpness-Aware Personalized Federated Learning AAAI 2025
SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAM AAAI 2025
Beyond Local Sharpness: Communication-Efficient Global Sharpness-aware Minimization for Federated Learning CVPR 2025
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes CVPR 2025
The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation CVPR 2025
SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025
Understanding Flatness in Generative Models: Its Role and Benefits ICCV 2025
Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations NAACL 2025
Enhancing LLM Knowledge Learning through Generalization EMNLP 2025