{"list":"other","total":54,"rows":[{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"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":"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":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"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":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"1607.05447","title":"On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization","created":"2016-07-19","cited_by_count":112},{"id":"1907.09356","title":"Decentralized Deep Learning with Arbitrary Communication Compression","created":"2019-07-22","cited_by_count":111},{"id":"1602.00591","title":"NEXT: In-Network Nonconvex Optimization","created":"2016-02-01","cited_by_count":107},{"id":"1805.11454","title":"Distributed Stochastic Gradient Tracking Methods","created":"2018-05-25","cited_by_count":106},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2308.08165","title":"Stochastic Controlled Averaging for Federated Learning with Communication Compression","created":"2023-08-16","cited_by_count":101},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"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":"1910.01727","title":"Generalized Inner Loop Meta-Learning","created":"2019-10-03","cited_by_count":93},{"id":"1803.06443","title":"Communication Compression for Decentralized Training","created":"2018-03-17","cited_by_count":88},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2008.12284","title":"learn2learn: A Library for Meta-Learning Research","created":"2020-08-27","cited_by_count":69},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69},{"id":"2006.09486","title":"Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters","created":"2020-06-16","cited_by_count":65},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60},{"id":"1909.06576","title":"Torchmeta: A Meta-Learning library for PyTorch","created":"2019-09-14","cited_by_count":52},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"2002.12688","title":"Decentralized gradient methods: does topology matter?","created":"2020-02-28","cited_by_count":35},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31},{"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":"2005.00797","title":"Multi-consensus Decentralized Accelerated Gradient Descent","created":"2020-05-02","cited_by_count":20},{"id":"2110.05282","title":"Optimal Gradient Tracking for Decentralized Optimization","created":"2021-10-11","cited_by_count":18},{"id":"2302.05412","title":"Achieving Linear Speedup in Non-IID Federated Bilevel Learning","created":"2023-02-10","cited_by_count":18},{"id":"2401.09587","title":"Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis","created":"2024-01-17","cited_by_count":15},{"id":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13},{"id":"2402.07101","title":"On the Complexity of First-Order Methods in Stochastic Bilevel Optimization","created":"2024-02-11","cited_by_count":12},{"id":"2304.07504","title":"Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis","created":"2023-04-15","cited_by_count":11},{"id":"2311.08945","title":"A Single-Loop Algorithm for Decentralized Bilevel Optimization","created":"2023-11-15","cited_by_count":7},{"id":"2404.00158","title":"Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing","created":"2024-03-29","cited_by_count":6},{"id":"2302.09766","title":"A One-Sample Decentralized Proximal Algorithm for Non-Convex Stochastic Composite Optimization","created":"2023-02-20","cited_by_count":4},{"id":"2312.03807","title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","created":"2023-12-06","cited_by_count":2},{"id":"2406.02939","title":"Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes","created":"2024-06-05","cited_by_count":1}],"next_cursor":null}