{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"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":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1711.00141","title":"Training GANs with Optimism","created":"2017-10-31","cited_by_count":217},{"id":"1404.6264","title":"EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization","created":"2014-04-24","cited_by_count":160},{"id":"1811.10792","title":"Stochastic Gradient Push for Distributed Deep Learning","created":"2018-11-27","cited_by_count":152},{"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":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"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":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"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":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"1808.07576","title":"Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms","created":"2018-08-22","cited_by_count":106},{"id":"2011.00364","title":"Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization","created":"2020-10-31","cited_by_count":96},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1907.04232","title":"Unified Optimal Analysis of the (Stochastic) Gradient Method","created":"2019-07-09","cited_by_count":82},{"id":"1610.05202","title":"Decentralized Collaborative Learning of Personalized Models over Networks","created":"2016-10-17","cited_by_count":76},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"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":"1705.08435","title":"Personalized and Private Peer-to-Peer Machine Learning","created":"2017-05-23","cited_by_count":54},{"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":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49},{"id":"1701.03961","title":"Communication-Efficient Algorithms for Decentralized and Stochastic Optimization","created":"2017-01-14","cited_by_count":43},{"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":"1901.00451","title":"SGD Converges to Global Minimum in Deep Learning via Star-convex Path","created":"2019-01-02","cited_by_count":39},{"id":"1905.11373","title":"Revisiting Stochastic Extragradient","created":"2019-05-27","cited_by_count":35},{"id":"1703.00260","title":"Extragradient method with variance reduction for stochastic variational inequalities","created":"2017-03-01","cited_by_count":33},{"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":"1809.00710","title":"A Dual Approach for Optimal Algorithms in Distributed Optimization over Networks","created":"2018-09-03","cited_by_count":27},{"id":"1907.07346","title":"$\\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression","created":"2019-07-17","cited_by_count":22},{"id":"1806.03915","title":"Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters","created":"2018-06-11","cited_by_count":21},{"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":"2106.04469","title":"Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks","created":"2021-06-08","cited_by_count":19},{"id":"1910.14380","title":"A Decentralized Proximal Point-type Method for Saddle Point Problems","created":"2019-10-31","cited_by_count":17},{"id":"2006.14567","title":"Taming GANs with Lookahead-Minmax","created":"2020-06-25","cited_by_count":16},{"id":"2007.04528","title":"Higher-order methods for convex-concave min-max optimization and monotone variational inequalities","created":"2020-07-09","cited_by_count":16},{"id":"2104.12676","title":"Solving a class of non-convex min-max games using adaptive momentum methods","created":"2021-04-26","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":"1802.09022","title":"An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization","created":"2018-02-25","cited_by_count":8},{"id":"2102.06780","title":"Newton Method over Networks is Fast up to the Statistical Precision","created":"2021-02-12","cited_by_count":7},{"id":"2103.14392","title":"An Accelerated Second-Order Method for Distributed Stochastic Optimization","created":"2021-03-26","cited_by_count":6},{"id":"2103.15598","title":"An Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs","created":"2021-03-29","cited_by_count":6},{"id":"2102.08246","title":"Hyperfast Second-Order Local Solvers for Efficient Statistically Preconditioned Distributed Optimization","created":"2021-02-16","cited_by_count":5}],"next_cursor":null}