{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"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":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"id":"1902.09843","title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","created":"2019-02-26","cited_by_count":183},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"1805.08114","title":"On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes","created":"2018-05-21","cited_by_count":156},{"id":"1610.02581","title":"Variance-based regularization with convex objectives","created":"2016-10-08","cited_by_count":155},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"2108.08647","title":"Multi-Center Federated Learning: Clients Clustering for Better Personalization","created":"2021-08-19","cited_by_count":113},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"2102.12660","title":"Distributionally Robust Federated Averaging","created":"2021-02-25","cited_by_count":104},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99},{"id":"1411.3803","title":"Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functions","created":"2014-11-14","cited_by_count":95},{"id":"1806.06763","title":"Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks","created":"2018-06-18","cited_by_count":90},{"id":"2204.10836","title":"Federated Learning Enables Big Data for Rare Cancer Boundary Detection","created":"2022-04-22","cited_by_count":84},{"id":"2105.03494","title":"The iWildCam 2021 Competition Dataset","created":"2021-05-07","cited_by_count":77},{"id":"1611.02189","title":"CoCoA: A General Framework for Communication-Efficient Distributed Optimization","created":"2016-11-07","cited_by_count":69},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"1705.08826","title":"Learning with Average Top-k Loss","created":"2017-05-24","cited_by_count":52},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50},{"id":"2006.10138","title":"An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives","created":"2020-06-17","cited_by_count":42},{"id":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40},{"id":"1912.03194","title":"Why are Adaptive Methods Good for Attention Models?","created":"2019-12-06","cited_by_count":35},{"id":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34},{"id":"2203.00176","title":"When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee","created":"2022-03-01","cited_by_count":29},{"id":"2202.12396","title":"Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications","created":"2022-02-24","cited_by_count":27},{"id":"2207.08540","title":"Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization","created":"2022-07-18","cited_by_count":16},{"id":"2210.05740","title":"Stochastic Constrained DRO with a Complexity Independent of Sample Size","created":"2022-10-11","cited_by_count":16},{"id":"2210.14396","title":"FeDXL: Provable Federated Learning for Deep X-Risk Optimization","created":"2022-10-26","cited_by_count":11},{"id":"2205.15614","title":"Communication-Efficient Distributionally Robust Decentralized Learning","created":"2022-05-31","cited_by_count":10},{"id":"2310.03234","title":"Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization","created":"2023-10-05","cited_by_count":10},{"id":"2012.06951","title":"Attentional-Biased Stochastic Gradient Descent","created":"2020-12-13","cited_by_count":9},{"id":"2307.13381","title":"Scaff-PD: Communication Efficient Fair and Robust Federated Learning","created":"2023-07-25","cited_by_count":6},{"id":"2208.13810","title":"DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs","created":"2022-08-29","cited_by_count":5},{"id":"2305.13170","title":"Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning","created":"2023-05-22","cited_by_count":5},{"id":"2203.05117","title":"Optimal Methods for Convex Risk Averse Distributed Optimization","created":"2022-03-10","cited_by_count":2}],"next_cursor":null}