flat minimum

Improving Generalization of Deep Neural Networks by Optimum Shifting AAAI 2025 Deep linear networks for regression are implicitly regularized towards flat minima NeurIPS 2024 Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification NeurIPS 2024 Gradient Alignment for Cross-Domain Face Anti-Spoofing CVPR 2024 Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning WACV 2024 An SDE for Modeling SAM: Theory and Insights ICML 2023 Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow ICLR 2023 Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution NeurIPS 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 PoF: Post-Training of Feature Extractor for Improving Generalization ICML 2022 Power-Law Escape Rate of SGD ICML 2022 Sharpness-Aware Training for Free NeurIPS 2022 The alignment property of SGD noise and how it helps select flat minima: A stability analysis NeurIPS 2022 Directional Pruning of Deep Neural Networks NeurIPS 2020 Unique Properties of Flat Minima in Deep Networks ICML 2020 Asymmetric Valleys: Beyond Sharp and Flat Local Minima NeurIPS 2019 Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience ICLR 2019