{"list":"other","total":61,"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":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"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":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"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":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"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":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"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":"1607.03218","title":"Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs","created":"2016-07-12","cited_by_count":150},{"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":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1709.08765","title":"Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization","created":"2017-09-26","cited_by_count":122},{"id":"2005.01350","title":"A Finite Time Analysis of Two Time-Scale Actor Critic Methods","created":"2020-05-04","cited_by_count":122},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"1611.03199","title":"Low Data Drug Discovery with One-shot Learning","created":"2016-11-10","cited_by_count":91},{"id":"2006.04045","title":"A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton","created":"2020-06-07","cited_by_count":79},{"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":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63},{"id":"1908.10831","title":"Stochastic AUC Maximization with Deep Neural Networks","created":"2019-08-28","cited_by_count":61},{"id":"1706.07880","title":"Collaborative Deep Learning in Fixed Topology Networks","created":"2017-06-23","cited_by_count":60},{"id":"2106.07991","title":"A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization","created":"2021-06-15","cited_by_count":60},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60},{"id":"1307.5561","title":"On the Linear Convergence of the ADMM in Decentralized Consensus Optimization","created":"2013-07-21","cited_by_count":57},{"id":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46},{"id":"1701.03961","title":"Communication-Efficient Algorithms for Decentralized and Stochastic Optimization","created":"2017-01-14","cited_by_count":43},{"id":"1608.05766","title":"On Nonconvex Decentralized Gradient Descent","created":"2016-08-20","cited_by_count":42},{"id":"1909.03510","title":"Bi-level Actor-Critic for Multi-agent Coordination","created":"2019-09-08","cited_by_count":39},{"id":"2104.08736","title":"Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence","created":"2021-04-18","cited_by_count":35},{"id":"1905.03218","title":"MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records","created":"2019-05-08","cited_by_count":33},{"id":"1911.03432","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","created":"2019-11-08","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":"2009.00690","title":"Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee","created":"2020-09-01","cited_by_count":28},{"id":"2107.12301","title":"Enhanced Bilevel Optimization via Bregman Distance","created":"2021-07-26","cited_by_count":28},{"id":"2010.02870","title":"Dif-MAML: Decentralized Multi-Agent Meta-Learning","created":"2020-10-06","cited_by_count":26},{"id":"2206.05670","title":"Decentralized Bilevel Optimization","created":"2022-06-12","cited_by_count":23},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20},{"id":"2206.15025","title":"On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network","created":"2022-06-30","cited_by_count":14},{"id":"2009.13357","title":"BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning","created":"2020-09-28","cited_by_count":10},{"id":"2207.13283","title":"INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks","created":"2022-07-27","cited_by_count":8},{"id":"1802.05811","title":"Distributed Stochastic Optimization via Adaptive SGD","created":"2018-02-16","cited_by_count":7},{"id":"2211.01122","title":"Fast Adaptive Federated Bilevel Optimization","created":"2022-11-02","cited_by_count":7},{"id":"1304.5590","title":"Distributed Constrained Optimization by Consensus-Based Primal-Dual Perturbation Method","created":"2013-04-20","cited_by_count":5}],"next_cursor":null}