{"list":"other","total":77,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"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":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"1711.00141","title":"Training GANs with Optimism","created":"2017-10-31","cited_by_count":217},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193},{"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":"1610.02581","title":"Variance-based regularization with convex objectives","created":"2016-10-08","cited_by_count":155},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"1902.08297","title":"Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods","created":"2019-02-21","cited_by_count":148},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"id":"1807.02629","title":"Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile","created":"2018-07-07","cited_by_count":136},{"id":"2002.02417","title":"Near-Optimal Algorithms for Minimax Optimization","created":"2020-02-05","cited_by_count":119},{"id":"1802.06175","title":"An Alternative View: When Does SGD Escape Local Minima?","created":"2018-02-17","cited_by_count":115},{"id":"2102.12660","title":"Distributionally Robust Federated Averaging","created":"2021-02-25","cited_by_count":104},{"id":"2006.08907","title":"Robust Federated Learning: The Case of Affine Distribution Shifts","created":"2020-06-16","cited_by_count":102},{"id":"1710.08402","title":"Stability and Generalization of Learning Algorithms that Converge to Global Optima","created":"2017-10-23","cited_by_count":100},{"id":"2011.00364","title":"Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization","created":"2020-10-31","cited_by_count":96},{"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":"2009.09623","title":"The Complexity of Constrained Min-Max Optimization","created":"2020-09-21","cited_by_count":82},{"id":"2001.03724","title":"Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems","created":"2020-01-11","cited_by_count":77},{"id":"1808.02901","title":"Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems","created":"2018-08-08","cited_by_count":76},{"id":"1907.01543","title":"Efficient Algorithms for Smooth Minimax Optimization","created":"2019-07-02","cited_by_count":76},{"id":"2102.07922","title":"Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm","created":"2021-02-16","cited_by_count":73},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72},{"id":"2006.06954","title":"Towards Flexible Device Participation in Federated Learning","created":"2020-06-12","cited_by_count":65},{"id":"1810.02060","title":"Weakly-Convex Concave Min-Max Optimization: Provable Algorithms and Applications in Machine Learning","created":"2018-10-04","cited_by_count":63},{"id":"2106.02326","title":"Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems","created":"2021-06-04","cited_by_count":62},{"id":"1605.00125","title":"Efficiency of minimizing compositions of convex functions and smooth maps","created":"2016-04-30","cited_by_count":59},{"id":"2010.15768","title":"A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems","created":"2020-10-29","cited_by_count":58},{"id":"2006.02032","title":"A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems","created":"2020-06-03","cited_by_count":57},{"id":"1902.08294","title":"Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications","created":"2019-02-21","cited_by_count":55},{"id":"2006.09065","title":"The limits of min-max optimization algorithms: convergence to spurious non-critical sets","created":"2020-06-16","cited_by_count":50},{"id":"2112.05604","title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","created":"2021-12-10","cited_by_count":49},{"id":"2103.15888","title":"The Complexity of Nonconvex-Strongly-Concave Minimax Optimization","created":"2021-03-29","cited_by_count":45},{"id":"1910.12999","title":"A Decentralized Parallel Algorithm for Training Generative Adversarial Nets","created":"2019-10-28","cited_by_count":43},{"id":"2102.13152","title":"Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency","created":"2021-02-25","cited_by_count":40},{"id":"1906.11985","title":"Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond","created":"2019-06-27","cited_by_count":36},{"id":"2104.08708","title":"Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization","created":"2021-04-18","cited_by_count":36},{"id":"2105.03793","title":"Stability and Generalization of Stochastic Gradient Methods for Minimax Problems","created":"2021-05-08","cited_by_count":36},{"id":"2006.06359","title":"Improved Algorithms for Convex-Concave Minimax Optimization","created":"2020-06-11","cited_by_count":34},{"id":"1906.03563","title":"Adversarial Attack Generation Empowered by Min-Max Optimization","created":"2019-06-09","cited_by_count":32},{"id":"2005.02426","title":"Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks","created":"2020-05-05","cited_by_count":27},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25},{"id":"2008.10103","title":"Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning","created":"2020-08-23","cited_by_count":24},{"id":"2102.04635","title":"Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity","created":"2021-02-09","cited_by_count":21},{"id":"2102.06333","title":"Efficient Algorithms for Federated Saddle Point Optimization","created":"2021-02-12","cited_by_count":20},{"id":"2106.04759","title":"Communication-efficient SGD: From Local SGD to One-Shot Averaging","created":"2021-06-09","cited_by_count":19},{"id":"2102.04653","title":"Proximal Gradient Descent-Ascent: Variable Convergence under K{\\L} Geometry","created":"2021-02-09","cited_by_count":18},{"id":"1910.14380","title":"A Decentralized Proximal Point-type Method for Saddle Point Problems","created":"2019-10-31","cited_by_count":17},{"id":"1512.09295","title":"Strategies and Principles of Distributed Machine Learning on Big Data","created":"2015-12-31","cited_by_count":16},{"id":"2106.01761","title":"Near Optimal Stochastic Algorithms for Finite-Sum Unbalanced Convex-Concave Minimax Optimization","created":"2021-06-03","cited_by_count":16},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15},{"id":"2102.07758","title":"Decentralized Distributed Optimization for Saddle Point Problems","created":"2021-02-15","cited_by_count":10},{"id":"2110.08477","title":"FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation","created":"2021-10-16","cited_by_count":9},{"id":"2010.04937","title":"On The Convergence of First Order Methods for Quasar-Convex Optimization","created":"2020-10-10","cited_by_count":8},{"id":"2107.10706","title":"Distributed Saddle-Point Problems Under Similarity","created":"2021-07-22","cited_by_count":8},{"id":"2107.05957","title":"Near-Optimal Decentralized Algorithms for Saddle Point Problems over Time-Varying Networks","created":"2021-07-13","cited_by_count":7},{"id":"1402.0589","title":"Protecting Privacy through Distributed Computation in Multi-agent Decision Making","created":"2014-02-04","cited_by_count":5},{"id":"2010.13359","title":"A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients","created":"2020-10-26","cited_by_count":2}],"next_cursor":null}