{"total":30,"rows":[{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2104.13467","title":"An optical neural network using less than 1 photon per multiplication","created":"2021-04-27","cited_by_count":30,"area":null},{"id":"2103.02351","title":"Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates","created":"2021-03-03","cited_by_count":17,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2206.10189","title":"A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","cited_by_count":10,"area":null},{"id":"2305.05933","title":"Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2212.10522","title":"Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2510.22440","title":"Low-Precision Streaming PCA","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2303.04676","title":"Considerations on the Theory of Training Models with Differential Privacy","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2308.09187","title":"Distributed Extra-gradient with Optimal Complexity and Communication Guarantees","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2102.09030","title":"Proactive DP: A Multple Target Optimization Framework for DP-SGD","created":"2021-02-17","cited_by_count":1,"area":null},{"id":"2112.13935","title":"AET-SGD: Asynchronous Event-triggered Stochastic Gradient Descent","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2203.06638","title":"Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGD","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2210.02882","title":"Scaling up Stochastic Gradient Descent for Non-convex Optimisation","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2211.03972","title":"Quantization-Based Optimization: Alternative Stochastic Approximation of Global Optimization","created":"2022-11-08","cited_by_count":1,"area":null},{"id":"2405.16966","title":"Dual-Delayed Asynchronous SGD for Arbitrarily Heterogeneous Data","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2410.15620","title":"Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2512.13583","title":"DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.07021","title":"Tight Analysis of Decentralized SGD: A Markov Chain Perspective","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2104.13818","title":"NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2105.03527","title":"Scalable Projection-Free Optimization","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2106.03211","title":"Distributed Learning and its Application for Time-Series Prediction","created":"2021-06-06","cited_by_count":0,"area":null},{"id":"2109.15292","title":"Accelerating Perturbed Stochastic Iterates in Asynchronous Lock-Free Optimization","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2305.18864","title":"Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2312.03120","title":"The Landscape of Modern Machine Learning: A Review of Machine, Distributed and Federated Learning","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2602.18002","title":"Asynchronous Heavy-Tailed Optimization","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.08211","title":"Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning Aggregation","created":"2026-03-09","cited_by_count":0,"area":null}],"next_cursor":null}