{"list":"other","total":55,"rows":[{"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"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":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"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":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"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":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"1902.06156","title":"A Little Is Enough: Circumventing Defenses For Distributed Learning","created":"2019-02-16","cited_by_count":288},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"2010.01243","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","created":"2020-10-03","cited_by_count":198},{"id":"2108.10252","title":"Federated Multi-Task Learning under a Mixture of Distributions","created":"2021-08-23","cited_by_count":192},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153},{"id":"2003.08673","title":"Survey of Personalization Techniques for Federated Learning","created":"2020-03-19","cited_by_count":145},{"id":"1903.03936","title":"Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation","created":"2019-03-10","cited_by_count":141},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"1507.08752","title":"An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback","created":"2015-07-31","cited_by_count":111},{"id":"2201.13409","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","created":"2022-01-31","cited_by_count":99},{"id":"1902.10710","title":"High probability generalization bounds for uniformly stable algorithms with nearly optimal rate","created":"2019-02-27","cited_by_count":98},{"id":"2105.05883","title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","created":"2021-05-12","cited_by_count":93},{"id":"2102.04671","title":"A Single-Timescale Method for Stochastic Bilevel Optimization","created":"2021-02-09","cited_by_count":69},{"id":"2012.00661","title":"Fast-Convergent Federated Learning with Adaptive Weighting","created":"2020-12-01","cited_by_count":67},{"id":"2112.11256","title":"Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling","created":"2021-12-21","cited_by_count":66},{"id":"2007.13137","title":"Fast-Convergent Federated Learning","created":"2020-07-26","cited_by_count":61},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"2007.15197","title":"Communication-Efficient Federated Learning via Optimal Client Sampling","created":"2020-07-30","cited_by_count":39},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"2202.06187","title":"On the Convergence of Clustered Federated Learning","created":"2022-02-13","cited_by_count":31},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26},{"id":"2210.07881","title":"Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate","created":"2022-10-14","cited_by_count":25},{"id":"2106.13044","title":"Personalized Federated Learning with Contextualized Generalization","created":"2021-06-24","cited_by_count":23},{"id":"2105.14095","title":"Weighted Training for Cross-Task Learning","created":"2021-05-28","cited_by_count":22},{"id":"2107.07190","title":"Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes","created":"2021-07-15","cited_by_count":13},{"id":"2201.12289","title":"The Power of First-Order Smooth Optimization for Black-Box Non-Smooth Problems","created":"2022-01-28","cited_by_count":9},{"id":"2211.13566","title":"Randomized gradient-free methods in convex optimization","created":"2022-11-24","cited_by_count":7},{"id":"2207.10751","title":"Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization","created":"2022-07-21","cited_by_count":6}],"next_cursor":null}