{"total":25,"rows":[{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"area":null},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2210.00102","title":"MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2104.12081","title":"How Well Does Self-Supervised Pre-Training Perform with Streaming Data?","created":"2021-04-25","cited_by_count":29,"area":null},{"id":"2412.01505","title":"Scaling Law for Language Models Training Considering Batch Size","created":"2024-12-02","cited_by_count":22,"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":"2107.04228","title":"Activated Gradients for Deep Neural Networks","created":"2021-07-09","cited_by_count":14,"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":"2103.01496","title":"DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing","created":"2021-03-02","cited_by_count":10,"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":"2406.13137","title":"Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models","created":"2024-06-19","cited_by_count":7,"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":"2101.02944","title":"BN-invariant sharpness regularizes the training model to better generalization","created":"2021-01-08","cited_by_count":3,"area":null},{"id":"2309.11305","title":"Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2408.04065","title":"Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?","created":"2024-08-07","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":"2202.09052","title":"Tackling benign nonconvexity with smoothing and stochastic gradients","created":"2022-02-18","cited_by_count":2,"area":null},{"id":"2205.07372","title":"Effect of Batch Normalization on Noise Resistant Property of Deep Learning Models","created":"2022-05-15","cited_by_count":2,"area":null},{"id":"2502.12384","title":"Scalable Back-Propagation-Free Training of Optical Physics-Informed Neural Networks","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2404.19725","title":"CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographics","created":"2024-04-30","cited_by_count":1,"area":null},{"id":"2302.09376","title":"Why is parameter averaging beneficial in SGD? An objective smoothing perspective","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2309.14601","title":"Neuro-Visualizer: An Auto-encoder-based Loss Landscape Visualization Method","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2403.18946","title":"Random Aggregate Beamforming for Over-the-Air Federated Learning in Large-Scale Networks","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2609.33437","title":"SMAT: Simple and Efficient Merge-Aware Training","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}