{"total":74,"rows":[{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415,"area":null},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"area":null},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137,"area":null},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122,"area":null},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95,"area":null},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42,"area":null},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41,"area":null},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38,"area":null},{"id":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31,"area":null},{"id":"2303.13087","title":"Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization","created":"2023-03-23","cited_by_count":29,"area":null},{"id":"2310.07269","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2206.04613","title":"Explicit Regularization in Overparametrized Models via Noise Injection","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2305.15287","title":"The Crucial Role of Normalization in Sharpness-Aware Minimization","created":"2023-05-24","cited_by_count":26,"area":null},{"id":"2111.12273","title":"Sharpness-aware Quantization for Deep Neural Networks","created":"2021-11-24","cited_by_count":25,"area":null},{"id":"2212.04983","title":"Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks","created":"2022-12-09","cited_by_count":21,"area":null},{"id":"2405.03676","title":"Why is SAM Robust to Label Noise?","created":"2024-05-06","cited_by_count":21,"area":null},{"id":"2409.14396","title":"Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape","created":"2024-09-22","cited_by_count":20,"area":null},{"id":"2301.12554","title":"Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing","created":"2023-01-29","cited_by_count":18,"area":null},{"id":"2305.12133","title":"Loss Spike in Training Neural Networks","created":"2023-05-20","cited_by_count":16,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2203.09962","title":"Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2112.06658","title":"Learning to Learn Transferable Attack","created":"2021-12-10","cited_by_count":13,"area":null},{"id":"2207.12203","title":"Improving Adversarial Robustness via Mutual Information Estimation","created":"2022-07-25","cited_by_count":13,"area":null},{"id":"2210.06895","title":"GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2404.00357","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","created":"2024-03-30","cited_by_count":13,"area":null},{"id":"2210.05398","title":"Continual Learning by Modeling Intra-Class Variation","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10,"area":null},{"id":"2105.08007","title":"Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2211.11489","title":"Efficient Generalization Improvement Guided by Random Weight Perturbation","created":"2022-11-21","cited_by_count":8,"area":null},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2403.02571","title":"DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2306.13239","title":"The Inductive Bias of Flatness Regularization for Deep Matrix Factorization","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2410.22656","title":"Tilted Sharpness-Aware Minimization","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2106.05009","title":"Network insensitivity to parameter noise via adversarial regularization","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2305.10713","title":"Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2309.06337","title":"Exploring Flat Minima for Domain Generalization with Large Learning Rates","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2511.03548","title":"Flat Minima and Generalization: Insights from Stochastic Convex Optimization","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2110.00199","title":"Perturbated Gradients Updating within Unit Space for Deep Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2206.00823","title":"Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules","created":"2022-06-02","cited_by_count":3,"area":null},{"id":"2404.17768","title":"Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization","created":"2024-04-27","cited_by_count":3,"area":null},{"id":"2503.14205","title":"Layer-wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning","created":"2025-03-18","cited_by_count":3,"area":null},{"id":"2509.04977","title":"Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2604.20614","title":"Too Sharp, Too Sure: When Calibration Follows Curvature","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2109.02889","title":"Adversarial Parameter Defense by Multi-Step Risk Minimization","created":"2021-09-07","cited_by_count":2,"area":null},{"id":"2205.10456","title":"PSO-Convolutional Neural Networks with Heterogeneous Learning Rate","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2207.01847","title":"PoF: Post-Training of Feature Extractor for Improving Generalization","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2311.15165","title":"Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2409.13173","title":"Bilateral Sharpness-Aware Minimization for Flatter Minima","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2505.23866","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2604.19740","title":"Generalization at the Edge of Stability","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2201.06064","title":"Neighborhood Region Smoothing Regularization for Finding Flat Minima In Deep Neural Networks","created":"2022-01-16","cited_by_count":1,"area":null},{"id":"2403.15210","title":"Early Period of Training Impacts Adaptation for Out-of-Distribution Generalization: An Empirical Study","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2512.12925","title":"Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2606.01827","title":"Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2308.03236","title":"G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2410.14667","title":"SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2411.01714","title":"1st-Order Magic: Analysis of Sharpness-Aware Minimization","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2509.21818","title":"Sharpness-Aware Minimization Can Hallucinate Minimizers","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2604.22170","title":"Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}