{"total":22,"rows":[{"id":"2112.08541","title":"BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing","created":"2021-12-16","cited_by_count":50,"area":null},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36,"area":null},{"id":"2403.07723","title":"On the Last-Iterate Convergence of Shuffling Gradient Methods","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2112.15287","title":"Distributed Random Reshuffling over Networks","created":"2021-12-31","cited_by_count":7,"area":null},{"id":"2301.10587","title":"On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems","created":"2023-01-25","cited_by_count":5,"area":null},{"id":"2409.08056","title":"Expansive Supervision for Neural Radiance Field","created":"2024-09-12","cited_by_count":5,"area":null},{"id":"2601.10237","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2109.03991","title":"The challenge of reproducible ML: an empirical study on the impact of bugs","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2507.11683","title":"PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2111.03820","title":"Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization","created":"2021-11-06","cited_by_count":2,"area":null},{"id":"2310.15976","title":"Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2403.16372","title":"SignSGD with Federated Voting","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2504.13266","title":"Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNs","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2603.03040","title":"cPNN: Continuous Progressive Neural Networks for Evolving Streaming Time Series","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2310.10102","title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2511.18611","title":"CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2606.15959","title":"Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2209.08729","title":"Data-driven and machine-learning based prediction of wave propagation behavior in dam-break flood","created":"2022-09-19","cited_by_count":0,"area":null},{"id":"2410.22297","title":"Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2510.23145","title":"Implicit Modeling for Transferability Estimation of Vision Foundation Models","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2608.22795","title":"VersaDB: A High-Performance AI Storage Database for Unifying Mutimodal Datasets","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}