{"list":"other","total":59,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"2006.09503","title":"Memory-Efficient Pipeline-Parallel DNN Training","created":"2020-06-16","cited_by_count":134},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"2002.11364","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","created":"2020-02-26","cited_by_count":90},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2008.00051","title":"On the Convergence of SGD with Biased Gradients","created":"2020-07-31","cited_by_count":83},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2102.02888","title":"1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed","created":"2021-02-04","cited_by_count":75},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61},{"id":"2104.14129","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","created":"2021-04-29","cited_by_count":61},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"1910.05124","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","created":"2019-10-09","cited_by_count":55},{"id":"1905.12938","title":"Stochastic Sign Descent Methods: New Algorithms and Better Theory","created":"2019-05-30","cited_by_count":49},{"id":"2001.01969","title":"Sparse Weight Activation Training","created":"2020-01-07","cited_by_count":45},{"id":"2010.00091","title":"Error Compensated Distributed SGD Can Be Accelerated","created":"2020-09-30","cited_by_count":45},{"id":"2010.12460","title":"Adaptive Gradient Quantization for Data-Parallel SGD","created":"2020-10-23","cited_by_count":45},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43},{"id":"1605.07991","title":"Efficient Distributed Learning with Sparsity","created":"2016-05-25","cited_by_count":38},{"id":"1705.01626","title":"Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks","created":"2017-05-03","cited_by_count":37},{"id":"1812.04056","title":"Accelerating Convolutional Neural Networks via Activation Map Compression","created":"2018-12-10","cited_by_count":34},{"id":"2101.10761","title":"An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems","created":"2021-01-26","cited_by_count":32},{"id":"1811.03619","title":"Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training","created":"2018-11-08","cited_by_count":28},{"id":"2007.13221","title":"CSER: Communication-efficient SGD with Error Reset","created":"2020-07-26","cited_by_count":27},{"id":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21},{"id":"1901.07988","title":"Backprop with Approximate Activations for Memory-efficient Network Training","created":"2019-01-23","cited_by_count":19},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13},{"id":"1903.02596","title":"Buddy Compression: Enabling Larger Memory for Deep Learning and HPC Workloads on GPUs","created":"2019-03-06","cited_by_count":11},{"id":"2010.08065","title":"FPRaker: A Processing Element For Accelerating Neural Network Training","created":"2020-10-15","cited_by_count":6},{"id":"2011.09017","title":"A Novel Memory-Efficient Deep Learning Training Framework via Error-Bounded Lossy Compression","created":"2020-11-18","cited_by_count":5},{"id":"1808.05285","title":"DNN Feature Map Compression using Learned Representation over GF(2)","created":"2018-08-15","cited_by_count":2}],"next_cursor":null}