{"list":"other","total":54,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"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":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86},{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82},{"id":"1909.04715","title":"First Analysis of Local GD on Heterogeneous Data","created":"2019-09-10","cited_by_count":81},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"1903.01463","title":"SGD without Replacement: Sharper Rates for General Smooth Convex Functions","created":"2019-03-04","cited_by_count":61},{"id":"2002.08246","title":"A Unified Convergence Analysis for Shuffling-Type Gradient Methods","created":"2020-02-19","cited_by_count":58},{"id":"2006.06946","title":"SGD with shuffling: optimal rates without component convexity and large epoch requirements","created":"2020-06-12","cited_by_count":58},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"1803.06573","title":"On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient","created":"2018-03-17","cited_by_count":43},{"id":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40},{"id":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38},{"id":"2006.11573","title":"Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization","created":"2020-06-20","cited_by_count":36},{"id":"2007.00878","title":"On the Outsized Importance of Learning Rates in Local Update Methods","created":"2020-07-02","cited_by_count":36},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2302.03109","title":"On the Convergence of Federated Averaging with Cyclic Client Participation","created":"2023-02-06","cited_by_count":31},{"id":"2012.06188","title":"Recent Theoretical Advances in Non-Convex Optimization","created":"2020-12-11","cited_by_count":30},{"id":"2207.12891","title":"RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates","created":"2022-07-26","cited_by_count":28},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","cited_by_count":23},{"id":"2212.14370","title":"Can 5th Generation Local Training Methods Support Client Sampling? Yes!","created":"2022-12-29","cited_by_count":22},{"id":"2303.07160","title":"Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond","created":"2023-03-13","cited_by_count":22},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19},{"id":"2207.03957","title":"Communication Acceleration of Local Gradient Methods via an Accelerated Primal-Dual Algorithm with Inexact Prox","created":"2022-07-08","cited_by_count":19},{"id":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18},{"id":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","cited_by_count":18},{"id":"2106.06880","title":"Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems","created":"2021-06-12","cited_by_count":17},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12},{"id":"2306.03240","title":"Improving Accelerated Federated Learning with Compression and Importance Sampling","created":"2023-06-05","cited_by_count":8}],"next_cursor":null}