{"total":24,"rows":[{"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":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2505.23725","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","created":"2025-05-29","cited_by_count":18,"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":"2206.15143","title":"Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning","created":"2022-06-30","cited_by_count":7,"area":null},{"id":"2305.09628","title":"Faster Federated Learning with Decaying Number of Local SGD Steps","created":"2023-05-16","cited_by_count":4,"area":null},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2112.01433","title":"Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2210.12184","title":"A New Perspective for Understanding Generalization Gap of Deep Neural Networks Trained with Large Batch Sizes","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2309.13681","title":"Accelerating Large Batch Training via Gradient Signal to Noise Ratio (GSNR)","created":"2023-09-24","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":"2304.11692","title":"The Disharmony between BN and ReLU Causes Gradient Explosion, but is Offset by the Correlation between Activations","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2405.00482","title":"PackVFL: Efficient HE Packing for Vertical Federated Learning","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2503.11146","title":"Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning","created":"2025-03-14","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":"2308.03236","title":"G-Mix: A Generalized Mixup Learning Framework Towards Flat Minima","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2509.10537","title":"On Using Large-Batches in Federated Learning","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2603.18112","title":"Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}