{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"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":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"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":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"1610.02915","title":"Deep Pyramidal Residual Networks","created":"2016-10-10","cited_by_count":163},{"id":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"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":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92},{"id":"1412.6651","title":"Deep learning with Elastic Averaging SGD","created":"2014-12-20","cited_by_count":90},{"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":"2001.02312","title":"Stochastic Weight Averaging in Parallel: Large-Batch Training that Generalizes Well","created":"2020-01-07","cited_by_count":57},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49},{"id":"2305.11584","title":"Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape","created":"2023-05-19","cited_by_count":46},{"id":"1912.00528","title":"The intriguing role of module criticality in the generalization of deep networks","created":"2019-12-02","cited_by_count":40},{"id":"1509.05753","title":"Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses","created":"2015-09-18","cited_by_count":39},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37},{"id":"1606.07365","title":"Parallel SGD: When does averaging help?","created":"2016-06-23","cited_by_count":32},{"id":"2405.18890","title":"Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization","created":"2024-05-29","cited_by_count":28},{"id":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26},{"id":"1506.04449","title":"Compressing Convolutional Neural Networks","created":"2015-06-14","cited_by_count":25},{"id":"2304.03094","title":"PopulAtion Parameter Averaging (PAPA)","created":"2023-04-06","cited_by_count":23},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20},{"id":"2212.07224","title":"FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation","created":"2022-12-14","cited_by_count":16},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15},{"id":"1507.01239","title":"Experiments on Parallel Training of Deep Neural Network using Model Averaging","created":"2015-07-05","cited_by_count":14},{"id":"2404.00357","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","created":"2024-03-30","cited_by_count":13},{"id":"2405.17517","title":"WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average","created":"2024-05-27","cited_by_count":9},{"id":"2006.06377","title":"STL-SGD: Speeding Up Local SGD with Stagewise Communication Period","created":"2020-06-11","cited_by_count":8},{"id":"2211.11489","title":"Efficient Generalization Improvement Guided by Random Weight Perturbation","created":"2022-11-21","cited_by_count":8},{"id":"1905.10395","title":"Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models: Extension","created":"2019-05-24","cited_by_count":7},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5},{"id":"2403.04206","title":"GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models","created":"2024-03-07","cited_by_count":4}],"next_cursor":null}