{"list":"other","total":69,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"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":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"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":"1502.05767","title":"Automatic differentiation in machine learning: a survey","created":"2015-02-20","cited_by_count":855},{"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":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1803.01498","title":"Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates","created":"2018-03-05","cited_by_count":711},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1912.13445","title":"Robust Aggregation for Federated Learning","created":"2019-12-31","cited_by_count":317},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1905.03871","title":"Differentially Private Learning with Adaptive Clipping","created":"2019-05-09","cited_by_count":220},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"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":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","created":"2017-03-14","cited_by_count":118},{"id":"1906.04329","title":"Federated Learning for Emoji Prediction in a Mobile Keyboard","created":"2019-06-11","cited_by_count":118},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"id":"2102.08503","title":"Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications","created":"2021-02-16","cited_by_count":85},{"id":"1709.07417","title":"Neural Optimizer Search with Reinforcement Learning","created":"2017-09-21","cited_by_count":82},{"id":"2010.10154","title":"Federated Bayesian Optimization via Thompson Sampling","created":"2020-10-20","cited_by_count":77},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","created":"2018-03-06","cited_by_count":69},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55},{"id":"2103.05032","title":"Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning","created":"2021-03-08","cited_by_count":52},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"1903.10635","title":"Federated Learning Of Out-Of-Vocabulary Words","created":"2019-03-26","cited_by_count":51},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"1703.00441","title":"Learning to Optimize Neural Nets","created":"2017-03-01","cited_by_count":41},{"id":"2010.03246","title":"Optimal Gradient Compression for Distributed and Federated Learning","created":"2020-10-07","cited_by_count":39},{"id":"1804.00222","title":"Meta-Learning Update Rules for Unsupervised Representation Learning","created":"2018-03-31","cited_by_count":37},{"id":"2005.10406","title":"Training Keyword Spotting Models on Non-IID Data with Federated Learning","created":"2020-05-21","cited_by_count":36},{"id":"2211.01572","title":"FedTP: Federated Learning by Transformer Personalization","created":"2022-11-03","cited_by_count":36},{"id":"2108.02117","title":"FedJAX: Federated learning simulation with JAX","created":"2021-08-04","cited_by_count":32},{"id":"1906.06624","title":"Scalable Model Compression by Entropy Penalized Reparameterization","created":"2019-06-15","cited_by_count":31},{"id":"2206.09262","title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","created":"2022-06-18","cited_by_count":31},{"id":"2211.10844","title":"Learning to Generate Image Embeddings with User-level Differential Privacy","created":"2022-11-20","cited_by_count":23},{"id":"1912.13075","title":"Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters","created":"2019-12-30","cited_by_count":16},{"id":"2203.06338","title":"Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation","created":"2022-03-12","cited_by_count":16},{"id":"2201.02664","title":"Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory","created":"2022-01-07","cited_by_count":14},{"id":"2007.07869","title":"Gradient-based Hyperparameter Optimization Over Long Horizons","created":"2020-07-15","cited_by_count":12},{"id":"2108.06869","title":"FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning","created":"2021-08-16","cited_by_count":11},{"id":"2208.09432","title":"Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learning","created":"2022-08-19","cited_by_count":11},{"id":"2104.04657","title":"Meta-Learning Bidirectional Update Rules","created":"2021-04-10","cited_by_count":10},{"id":"2109.03973","title":"Iterated Vector Fields and Conservatism, with Applications to Federated Learning","created":"2021-09-08","cited_by_count":8},{"id":"2205.03494","title":"Online Model Compression for Federated Learning with Large Models","created":"2022-05-06","cited_by_count":7},{"id":"2209.04683","title":"Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models","created":"2022-09-10","cited_by_count":2},{"id":"2211.02106","title":"Federated Hypergradient Descent","created":"2022-11-03","cited_by_count":2}],"next_cursor":null}