{"list":"other","total":60,"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":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1501.01571","title":"An Introduction to Matrix Concentration Inequalities","created":"2015-01-07","cited_by_count":397},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1711.00141","title":"Training GANs with Optimism","created":"2017-10-31","cited_by_count":217},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"1802.10551","title":"A Variational Inequality Perspective on Generative Adversarial Networks","created":"2018-02-28","cited_by_count":144},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"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":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"2011.00364","title":"Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization","created":"2020-10-31","cited_by_count":96},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"id":"1802.06132","title":"Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks","created":"2018-02-16","cited_by_count":68},{"id":"1904.08598","title":"Reducing Noise in GAN Training with Variance Reduced Extragradient","created":"2019-04-18","cited_by_count":62},{"id":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"2008.12776","title":"Efficiently Solving MDPs with Stochastic Mirror Descent","created":"2020-08-28","cited_by_count":53},{"id":"2003.10162","title":"Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling","created":"2020-03-23","cited_by_count":49},{"id":"2102.08352","title":"Stochastic Variance Reduction for Variational Inequality Methods","created":"2021-02-16","cited_by_count":47},{"id":"2010.00091","title":"Error Compensated Distributed SGD Can Be Accelerated","created":"2020-09-30","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":"1703.00260","title":"Extragradient method with variance reduction for stochastic variational inequalities","created":"2017-03-01","cited_by_count":33},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32},{"id":"2102.01583","title":"The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication","created":"2021-02-02","cited_by_count":31},{"id":"2002.10726","title":"Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization","created":"2020-02-25","cited_by_count":30},{"id":"1311.2776","title":"On the Convergence Properties of Non-Euclidean Extragradient Methods for Variational Inequalities with Generalized Monotone Operators","created":"2013-11-12","cited_by_count":29},{"id":"1912.11940","title":"Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets","created":"2019-12-26","cited_by_count":29},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25},{"id":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","cited_by_count":23},{"id":"2102.06333","title":"Efficient Algorithms for Federated Saddle Point Optimization","created":"2021-02-12","cited_by_count":20},{"id":"1410.1628","title":"Optimal stochastic extragradient schemes for pseudomonotone stochastic variational inequality problems and their variants","created":"2014-10-07","cited_by_count":19},{"id":"1908.02246","title":"On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond","created":"2019-08-06","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":"2210.13831","title":"Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity","created":"2022-10-25","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":"2202.02771","title":"Optimal Algorithms for Decentralized Stochastic Variational Inequalities","created":"2022-02-06","cited_by_count":14},{"id":"1902.08949","title":"Training GANs with Centripetal Acceleration","created":"2019-02-24","cited_by_count":13},{"id":"2210.13277","title":"CompressedScaffnew: The First Theoretical Double Acceleration of Communication from Local Training and Compression in Distributed Optimization","created":"2022-10-24","cited_by_count":11},{"id":"2205.15136","title":"Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity","created":"2022-05-30","cited_by_count":10},{"id":"2208.13592","title":"Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey","created":"2022-08-29","cited_by_count":10},{"id":"2106.06075","title":"A Decentralized Adaptive Momentum Method for Solving a Class of Min-Max Optimization Problems","created":"2021-06-10","cited_by_count":9},{"id":"2109.14213","title":"On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization","created":"2021-09-29","cited_by_count":9},{"id":"2206.09446","title":"Compression and Data Similarity: Combination of Two Techniques for Communication-Efficient Solving of Distributed Variational Inequalities","created":"2022-06-19","cited_by_count":8}],"next_cursor":null}