Explore federated learning optimization with compression in this 59-minute presentation from Institut des Hautes Etudes Scientifiques (IHES). Dive into recent findings on convergence and compression rate tradeoffs, as well as user-heterogeneity impacts. Examine two key phenomena: the effect of user-heterogeneity on federated optimization methods under communication constraints, and the robustness of distributed stochastic algorithms to iterate perturbation. Learn about a novel compression scheme utilizing random codebooks and unitary invariant distributions. Gain insights from Aymeric Dieuleveut of CMAP/Ecole polytechnique on addressing challenges in federated learning with communication constraints.
Federated Learning with Communication Constraints: Challenges and Recent Results
Institut des Hautes Etudes Scientifiques (IHES) via YouTube
Overview
Syllabus
Aymeric Dieuleveut - Federated Learning with Communication Constraints: Challenges in (...)
Taught by
Institut des Hautes Etudes Scientifiques (IHES)
Related Courses
-
Heterogeneity-Aware Algorithms for Federated Optimization
-
Uncertainty Quantification in Machine Learning: Federated Conformal Prediction
-
Online Optimization Meets Federated Learning - Tutorial
-
Heterogeneity-Aware Algorithms for Federated Learning and Distributed Optimization
-
Privacy-Aware Compression for Federated Learning
-
Interaction Is Necessary for Distributed Learning with Privacy or Communication Constraints
