{"list":"other","total":80,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"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":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"1802.10551","title":"A Variational Inequality Perspective on Generative Adversarial Networks","created":"2018-02-28","cited_by_count":144},{"id":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"2005.01350","title":"A Finite Time Analysis of Two Time-Scale Actor Critic Methods","created":"2020-05-04","cited_by_count":122},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"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":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"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":"1807.03907","title":"The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization","created":"2018-07-11","cited_by_count":101},{"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":"2011.00364","title":"Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization","created":"2020-10-31","cited_by_count":96},{"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":"2006.07228","title":"FedGAN: Federated Generative Adversarial Networks for Distributed Data","created":"2020-06-12","cited_by_count":90},{"id":"1909.04715","title":"First Analysis of Local GD on Heterogeneous Data","created":"2019-09-10","cited_by_count":81},{"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":"1806.07811","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","created":"2018-06-20","cited_by_count":63},{"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":"1706.09156","title":"Non-convex Finite-Sum Optimization Via SCSG Methods","created":"2017-06-28","cited_by_count":61},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60},{"id":"2002.01268","title":"Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise","created":"2020-02-04","cited_by_count":53},{"id":"2201.01212","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","created":"2022-01-04","cited_by_count":49},{"id":"1607.07329","title":"Accelerating Stochastic Composition Optimization","created":"2016-07-25","cited_by_count":46},{"id":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41},{"id":"2102.13152","title":"Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency","created":"2021-02-25","cited_by_count":40},{"id":"2203.04850","title":"Federated Minimax Optimization: Improved Convergence Analyses and Algorithms","created":"2022-03-09","cited_by_count":37},{"id":"2011.01868","title":"Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance","created":"2020-11-03","cited_by_count":35},{"id":"2106.11396","title":"BiAdam: Fast Adaptive Bilevel Optimization Methods","created":"2021-06-21","cited_by_count":33},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32},{"id":"2102.03198","title":"Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning","created":"2021-02-05","cited_by_count":31},{"id":"1901.09109","title":"DADAM: A Consensus-based Distributed Adaptive Gradient Method for Online Optimization","created":"2019-01-25","cited_by_count":30},{"id":"1912.11940","title":"Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets","created":"2019-12-26","cited_by_count":29},{"id":"2008.10526","title":"Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates","created":"2020-08-24","cited_by_count":25},{"id":"1801.03600","title":"Multi-Level Stochastic Gradient Methods for Nested Composition Optimization","created":"2018-01-11","cited_by_count":24},{"id":"2206.05670","title":"Decentralized Bilevel Optimization","created":"2022-06-12","cited_by_count":23},{"id":"2102.06333","title":"Efficient Algorithms for Federated Saddle Point Optimization","created":"2021-02-12","cited_by_count":20},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20},{"id":"2302.05412","title":"Achieving Linear Speedup in Non-IID Federated Bilevel Learning","created":"2023-02-10","cited_by_count":18},{"id":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17},{"id":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15},{"id":"2212.10048","title":"Asynchronous Distributed Bilevel Optimization","created":"2022-12-20","cited_by_count":13},{"id":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13},{"id":"2105.13954","title":"A Gradient Method for Multilevel Optimization","created":"2021-05-28","cited_by_count":12},{"id":"2106.11264","title":"Compositional federated learning: Applications in distributionally robust averaging and meta learning","created":"2021-06-21","cited_by_count":12},{"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":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","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":"2302.04249","title":"Federated Minimax Optimization with Client Heterogeneity","created":"2023-02-08","cited_by_count":8},{"id":"2304.10101","title":"Federated Compositional Deep AUC Maximization","created":"2023-04-20","cited_by_count":8},{"id":"2211.01122","title":"Fast Adaptive Federated Bilevel Optimization","created":"2022-11-02","cited_by_count":7},{"id":"2211.01883","title":"Faster Adaptive Momentum-Based Federated Methods for Distributed Composition Optimization","created":"2022-11-03","cited_by_count":2},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","cited_by_count":2}],"next_cursor":null}