{"total":21,"rows":[{"id":"2107.06925","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","created":"2021-07-14","cited_by_count":68,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"area":null},{"id":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","cited_by_count":23,"area":null},{"id":"2106.00221","title":"Concurrent Adversarial Learning for Large-Batch Training","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2108.12074","title":"4-bit Quantization of LSTM-based Speech Recognition Models","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2111.09562","title":"COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression","created":"2021-11-18","cited_by_count":8,"area":null},{"id":"2108.03645","title":"Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2203.04738","title":"Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2207.11333","title":"Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2408.06018","title":"Uncertainty-Informed Volume Visualization using Implicit Neural Representation","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2106.07454","title":"NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning","created":"2021-06-14","cited_by_count":2,"area":null},{"id":"2201.12667","title":"Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity","created":"2022-01-29","cited_by_count":2,"area":null},{"id":"2406.18545","title":"Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2106.10796","title":"CD-SGD: Distributed Stochastic Gradient Descent with Compression and Delay Compensation","created":"2021-06-21","cited_by_count":0,"area":null},{"id":"2108.05839","title":"Logit Attenuating Weight Normalization","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2110.00791","title":"Optimizing Neural Network for Computer Vision task in Edge Device","created":"2021-10-02","cited_by_count":0,"area":null},{"id":"2302.05865","title":"Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization","created":"2023-02-12","cited_by_count":0,"area":null},{"id":"2401.10210","title":"Mastery Guided Non-parametric Clustering to Scale-up Strategy Prediction","created":"2024-01-04","cited_by_count":0,"area":null},{"id":"2505.00982","title":"DHO$_2$: Accelerating Distributed Hybrid Order Optimization via Model Parallelism and ADMM","created":"2025-05-02","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}