{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","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":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1912.13445","title":"Robust Aggregation for Federated Learning","created":"2019-12-31","cited_by_count":317},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"1509.02897","title":"Practical and Optimal LSH for Angular Distance","created":"2015-09-09","cited_by_count":106},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"2106.13673","title":"Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy","created":"2021-06-25","cited_by_count":69},{"id":"2007.11707","title":"Breaking the Communication-Privacy-Accuracy Trilemma","created":"2020-07-22","cited_by_count":68},{"id":"1903.06701","title":"Scaling Distributed Machine Learning with In-Network Aggregation","created":"2019-02-22","cited_by_count":65},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55},{"id":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52},{"id":"2002.08958","title":"Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor","created":"2020-02-20","cited_by_count":45},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"1611.07555","title":"Randomized Distributed Mean Estimation: Accuracy vs Communication","created":"2016-11-22","cited_by_count":39},{"id":"2010.03246","title":"Optimal Gradient Compression for Distributed and Federated Learning","created":"2020-10-07","cited_by_count":39},{"id":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32},{"id":"2202.00998","title":"3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation","created":"2022-02-02","cited_by_count":27},{"id":"2205.04180","title":"EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization","created":"2022-05-09","cited_by_count":17},{"id":"2106.03056","title":"MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization","created":"2021-06-06","cited_by_count":14},{"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":"2203.04925","title":"Correlated quantization for distributed mean estimation and optimization","created":"2022-03-09","cited_by_count":14},{"id":"2010.02331","title":"How to send a real number using a single bit (and some shared randomness)","created":"2020-10-05","cited_by_count":12},{"id":"2102.08374","title":"IntSGD: Adaptive Floatless Compression of Stochastic Gradients","created":"2021-02-16","cited_by_count":9},{"id":"2007.03731","title":"PINT: Probabilistic In-band Network Telemetry","created":"2020-07-07","cited_by_count":6},{"id":"2105.07829","title":"Compressed Communication for Distributed Training: Adaptive Methods and System","created":"2021-05-17","cited_by_count":5},{"id":"2004.10332","title":"Faster and More Accurate Measurement through Additive-Error Counters","created":"2020-04-21","cited_by_count":2},{"id":"1810.02899","title":"Memento: Making Sliding Windows Efficient for Heavy Hitters","created":"2018-10-05","cited_by_count":1},{"id":"2102.12531","title":"SALSA: Self-Adjusting Lean Streaming Analytics","created":"2021-02-24","cited_by_count":1},{"id":"2110.14224","title":"SOAR: Minimizing Network Utilization with Bounded In-network Computing","created":"2021-10-27","cited_by_count":1}],"next_cursor":null}