{"total":16,"rows":[{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632,"area":null},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2111.06483","title":"Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2302.08545","title":"THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression","created":"2023-02-16","cited_by_count":15,"area":null},{"id":"2102.10424","title":"GIST: Distributed Training for Large-Scale Graph Convolutional Networks","created":"2021-02-20","cited_by_count":10,"area":null},{"id":"2403.07128","title":"DrJAX: Scalable and Differentiable MapReduce Primitives in JAX","created":"2024-03-11","cited_by_count":9,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2107.06469","title":"Model-Parallel Model Selection for Deep Learning Systems","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2311.02909","title":"Distributed Matrix-Based Sampling for Graph Neural Network Training","created":"2023-11-06","cited_by_count":6,"area":null},{"id":"2102.01963","title":"Local Critic Training for Model-Parallel Learning of Deep Neural Networks","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2210.16169","title":"LOFT: Finding Lottery Tickets through Filter-wise Training","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2104.09075","title":"An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks","created":"2021-04-19","cited_by_count":2,"area":null},{"id":"2311.05726","title":"Neural Network Methods for Radiation Detectors and Imaging","created":"2023-11-09","cited_by_count":2,"area":null},{"id":"2406.17812","title":"Scalable Artificial Intelligence for Science: Perspectives, Methods and Exemplars","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2104.14658","title":"Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed","created":"2021-04-25","cited_by_count":0,"area":null}],"next_cursor":null}