{"list":"other","total":71,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"id":"2102.07623","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","created":"2021-02-15","cited_by_count":571},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"2001.05647","title":"Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results","created":"2020-01-16","cited_by_count":122},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"1810.07896","title":"Solving Linear Programs in the Current Matrix Multiplication Time","created":"2018-10-18","cited_by_count":100},{"id":"2010.02772","title":"InstaHide: Instance-hiding Schemes for Private Distributed Learning","created":"2020-10-06","cited_by_count":90},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"1611.02189","title":"CoCoA: A General Framework for Communication-Efficient Distributed Optimization","created":"2016-11-07","cited_by_count":69},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2006.11648","title":"Training (Overparametrized) Neural Networks in Near-Linear Time","created":"2020-06-20","cited_by_count":58},{"id":"2004.04250","title":"An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications","created":"2020-04-08","cited_by_count":57},{"id":"1905.04447","title":"Solving Empirical Risk Minimization in the Current Matrix Multiplication Time","created":"2019-05-11","cited_by_count":53},{"id":"2009.10217","title":"A Faster Interior Point Method for Semidefinite Programming","created":"2020-09-21","cited_by_count":53},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49},{"id":"1704.08246","title":"Relative Error Tensor Low Rank Approximation","created":"2017-04-26","cited_by_count":45},{"id":"1910.06001","title":"Federated Transfer Reinforcement Learning for Autonomous Driving","created":"2019-10-14","cited_by_count":44},{"id":"2004.07470","title":"Faster Dynamic Matrix Inverse for Faster LPs","created":"2020-04-16","cited_by_count":44},{"id":"2303.15725","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","created":"2023-03-28","cited_by_count":44},{"id":"1608.06879","title":"AIDE: Fast and Communication Efficient Distributed Optimization","created":"2016-08-24","cited_by_count":43},{"id":"1910.11957","title":"A Deterministic Linear Program Solver in Current Matrix Multiplication Time","created":"2019-10-25","cited_by_count":42},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37},{"id":"2211.06033","title":"A Faster Small Treewidth SDP Solver","created":"2022-11-11","cited_by_count":36},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35},{"id":"2010.06053","title":"TextHide: Tackling Data Privacy in Language Understanding Tasks","created":"2020-10-12","cited_by_count":33},{"id":"2101.08208","title":"Solving SDP Faster: A Robust IPM Framework and Efficient Implementation","created":"2021-01-20","cited_by_count":33},{"id":"2110.04622","title":"Does Preprocessing Help Training Over-parameterized Neural Networks?","created":"2021-10-09","cited_by_count":32},{"id":"1409.1458","title":"Communication-Efficient Distributed Dual Coordinate Ascent","created":"2014-09-04","cited_by_count":31},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31},{"id":"1405.7910","title":"Optimal CUR Matrix Decompositions","created":"2014-05-30","cited_by_count":29},{"id":"2011.05365","title":"A Nearly-Linear Time Algorithm for Linear Programs with Small Treewidth: A Multiscale Representation of Robust Central Path","created":"2020-11-10","cited_by_count":29},{"id":"2211.14227","title":"Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing","created":"2022-11-25","cited_by_count":29},{"id":"2210.08371","title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","created":"2022-10-15","cited_by_count":25},{"id":"1504.06729","title":"Optimal Principal Component Analysis in Distributed and Streaming Models","created":"2015-04-25","cited_by_count":24},{"id":"1310.2059","title":"Distributed Coordinate Descent Method for Learning with Big Data","created":"2013-10-08","cited_by_count":23},{"id":"1805.07674","title":"BourGAN: Generative Networks with Metric Embeddings","created":"2018-05-19","cited_by_count":22},{"id":"2208.04508","title":"Training Overparametrized Neural Networks in Sublinear Time","created":"2022-08-09","cited_by_count":22},{"id":"2208.05395","title":"A Sublinear Adversarial Training Algorithm","created":"2022-08-10","cited_by_count":22},{"id":"2210.12468","title":"Discrepancy Minimization in Input-Sparsity Time","created":"2022-10-22","cited_by_count":22},{"id":"1502.03508","title":"Adding vs. Averaging in Distributed Primal-Dual Optimization","created":"2015-02-12","cited_by_count":19},{"id":"1806.06430","title":"Subspace Embedding and Linear Regression with Orlicz Norm","created":"2018-06-17","cited_by_count":19},{"id":"1506.06840","title":"On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants","created":"2015-06-23","cited_by_count":18},{"id":"2208.03635","title":"Federated Adversarial Learning: A Framework with Convergence Analysis","created":"2022-08-07","cited_by_count":17},{"id":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15},{"id":"2303.12298","title":"A General Algorithm for Solving Rank-one Matrix Sensing","created":"2023-03-22","cited_by_count":15},{"id":"2212.11408","title":"Adaptive and Dynamic Multi-Resolution Hashing for Pairwise Summations","created":"2022-12-21","cited_by_count":14},{"id":"2302.00248","title":"A Nearly-Optimal Bound for Fast Regression with $\\ell_\\infty$ Guarantee","created":"2023-02-01","cited_by_count":14},{"id":"1601.07721","title":"Distributed Low Rank Approximation of Implicit Functions of a Matrix","created":"2016-01-28","cited_by_count":12},{"id":"2304.03426","title":"Convex Minimization with Integer Minima in $\\widetilde O(n^4)$ Time","created":"2023-04-07","cited_by_count":12},{"id":"2305.08367","title":"Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration","created":"2023-05-15","cited_by_count":11},{"id":"2208.03367","title":"Sublinear Time Algorithm for Online Weighted Bipartite Matching","created":"2022-08-05","cited_by_count":7},{"id":"2305.08353","title":"Fast and Efficient Matching Algorithm with Deadline Instances","created":"2023-05-15","cited_by_count":7},{"id":"1609.01361","title":"Fourier-sparse interpolation without a frequency gap","created":"2016-09-06","cited_by_count":6},{"id":"2205.14816","title":"Fast Distance Oracles for Any Symmetric Norm","created":"2022-05-30","cited_by_count":6},{"id":"1609.00896","title":"A Robust Sparse Fourier Transform in the Continuous Setting","created":"2016-09-04","cited_by_count":5},{"id":"1909.11123","title":"(Nearly) Sample-Optimal Sparse Fourier Transform in Any Dimension; RIPless and Filterless","created":"2019-09-24","cited_by_count":4},{"id":"2011.11181","title":"On InstaHide, Phase Retrieval, and Sparse Matrix Factorization","created":"2020-11-23","cited_by_count":4},{"id":"2211.14825","title":"Dynamic Kernel Graph Sparsifiers","created":"2022-11-27","cited_by_count":4},{"id":"2102.01570","title":"Symmetric Sparse Boolean Matrix Factorization and Applications","created":"2021-02-02","cited_by_count":3},{"id":"1311.0636","title":"A Parallel SGD method with Strong Convergence","created":"2013-11-04","cited_by_count":2},{"id":"1403.5804","title":"Sample-Optimal Fourier Sampling in Any Constant Dimension -- Part I","created":"2014-03-23","cited_by_count":2},{"id":"1604.00845","title":"Sparse Fourier Transform in Any Constant Dimension with Nearly-Optimal Sample Complexity in Sublinear Time","created":"2016-04-04","cited_by_count":2},{"id":"1708.04544","title":"Sample Efficient Estimation and Recovery in Sparse FFT via Isolation on Average","created":"2017-08-15","cited_by_count":2},{"id":"2208.09634","title":"An $O(k\\log n)$ Time Fourier Set Query Algorithm","created":"2022-08-20","cited_by_count":2},{"id":"1604.03763","title":"A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization","created":"2016-04-13","cited_by_count":1}],"next_cursor":null}