gradient norm

A Unified Perspective on Adversarial Membership Manipulation in Vision Models CVPR 2026 Optimization and Robustness-Informed Membership Inference Attacks for LLMs AAAI 2026 Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization AAAI 2025 Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective ICCV 2025 Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction EMNLP 2025 FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025 Instance-dependent Early Stopping ICLR 2025 Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN ICLR 2025 When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR ACL 2025 Clarifying the Behavior and the Difficulty of Adversarial Training AAAI 2024 FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning NeurIPS 2024 GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models AISTATS 2024 PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization NeurIPS 2024 Small-scale proxies for large-scale Transformer training instabilities ICLR 2024 The Price of Adaptivity in Stochastic Convex Optimization COLT 2024 Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NeurIPS 2024 When Will Gradient Regularization Be Harmful? ICML 2024 AdaNorm: Adaptive Gradient Norm Correction Based Optimizer for CNNs WACV 2023 Boosting Adversarial Transferability by Achieving Flat Local Maxima NeurIPS 2023 Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023 Disentangling the Mechanisms Behind Implicit Regularization in SGD ICLR 2023 Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization CVPR 2023 Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks NeurIPS 2023 Mitigating Dataset Bias by Using Per-Sample Gradient ICLR 2023 On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective NeurIPS 2023