{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2402.00838","title":"OLMo: Accelerating the Science of Language Models","created":"2024-02-01","cited_by_count":613},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"1810.07288","title":"Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron","created":"2018-10-16","cited_by_count":143},{"id":"1710.06451","title":"A Bayesian Perspective on Generalization and Stochastic Gradient Descent","created":"2017-10-17","cited_by_count":135},{"id":"1804.07795","title":"Stochastic subgradient method converges on tame functions","created":"2018-04-20","cited_by_count":124},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"1907.04232","title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","created":"2019-07-09","cited_by_count":82},{"id":"2010.00892","title":"Variance-Reduced Methods for Machine Learning","created":"2020-10-02","cited_by_count":79},{"id":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79},{"id":"1403.4699","title":"A Proximal Stochastic Gradient Method with Progressive Variance Reduction","created":"2014-03-19","cited_by_count":78},{"id":"1810.08313","title":"Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD","created":"2018-10-19","cited_by_count":77},{"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":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63},{"id":"1701.03961","title":"Communication-Efficient Algorithms for Decentralized and Stochastic Optimization","created":"2017-01-14","cited_by_count":43},{"id":"2402.16819","title":"Nemotron-4 15B Technical Report","created":"2024-02-26","cited_by_count":36},{"id":"2102.09743","title":"Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques","created":"2021-02-19","cited_by_count":34},{"id":"1612.05086","title":"Coupling Adaptive Batch Sizes with Learning Rates","created":"2016-12-15","cited_by_count":30},{"id":"1710.11258","title":"Adaptive Sampling Strategies for Stochastic Optimization","created":"2017-10-30","cited_by_count":30},{"id":"1712.02029","title":"AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks","created":"2017-12-06","cited_by_count":29},{"id":"2010.12998","title":"Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD","created":"2020-10-24","cited_by_count":26},{"id":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26},{"id":"2104.06069","title":"1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed","created":"2021-04-13","cited_by_count":24},{"id":"1711.04325","title":"Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes","created":"2017-11-12","cited_by_count":22},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20},{"id":"2007.05105","title":"AdaScale SGD: A User-Friendly Algorithm for Distributed Training","created":"2020-07-09","cited_by_count":16},{"id":"2310.20452","title":"AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms","created":"2023-10-31","cited_by_count":16},{"id":"1610.05792","title":"Big Batch SGD: Automated Inference using Adaptive Batch Sizes","created":"2016-10-18","cited_by_count":13},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8},{"id":"2306.11201","title":"Adaptive Federated Learning with Auto-Tuned Clients","created":"2023-06-19","cited_by_count":7},{"id":"2307.06306","title":"Locally Adaptive Federated Learning","created":"2023-07-12","cited_by_count":7},{"id":"2405.00017","title":"Queuing dynamics of asynchronous Federated Learning","created":"2024-02-12","cited_by_count":6},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5},{"id":"1808.01371","title":"Large Scale Language Modeling: Converging on 40GB of Text in Four Hours","created":"2018-08-03","cited_by_count":4},{"id":"2402.05264","title":"AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size","created":"2024-02-07","cited_by_count":3}],"next_cursor":null}